© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99268
    Prev
    Next
    INDEX
    Explanations

    Fusarium, Nd lasers, names

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific notation and technical terms, particularly "Nd" which appears frequently in chemical and physics contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron flags unusually rare or domain‐specific tokens (e.g. chemical element symbols like “Nd,” uncommon words like “Fus,” “NoSuch,” or other low‐frequency terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ῞
    -3.03
    躂
    -2.86
    蹌
    -2.84
    柺
    -2.75
    ଞ
    -2.75
    ᝢ
    -2.72
    螣
    -2.69
    暃
    -2.69
    𐌻
    -2.63
    ⢌
    -2.63
    POSITIVE LOGITS
    1
    2.88
    なんか
    2.63
    は
    2.59
     Until
    2.50
    "
    2.47
    する
    2.42
    なんて
    2.38
    ции
    2.38
    2
    2.38
    на
    2.36
    Activations Density 0.012%

    No Known Activations