© 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. 8470
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

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

    This neuron doesn’t respond to any sequence in the text (it’s effectively “dead” and fires on nothing).

    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
    of
    -2.50
    s
    -2.48
    mathrm
    -2.33
    when
    -2.31
    u
    -2.17
     betrayed
    -2.13
    there
    -2.03
    家が
    -2.03
    re
    -2.02
    x
    -2.02
    POSITIVE LOGITS
     และ
    2.91
    祧
    2.50
    に入れる
    2.45
    蘩
    2.33
    </em>
    2.16
    辄
    2.14
    骉
    2.11
    に入れ
    2.09
     localizada
    2.09
    ↵↵
    2.09
    Activations Density 0.021%

    No Known Activations