© 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. 22-GEMMASCOPE-RES-131K
    7. 129360
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to prominent content‐bearing technical nouns or keywords—especially domain‐specific terms often found in titles or headings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Technical terms and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    8
    -1.15
    良かったです
    -1.06
    providing
    -1.06
    ほんとに
    -1.05
    2
    -1.05
    我又
    -1.04
    ほとん
    -1.03
    かなりの
    -1.02
    5
    -1.02
     advierte
    -1.00
    POSITIVE LOGITS
     equation
    1.43
     equations
    1.09
     what
    1.03
    備考
    1.01
    arischen
    1.00
    אם
    1.00
     خونه
    1.00
    لوب
    0.98
    Ꮢ
    0.97
    förmig
    0.95
    Activations Density 0.109%

    No Known Activations