© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84031
    Prev
    Next
    INDEX
    Explanations

    numbers around 210

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

    The neuron is highly sensitive to the digit “0” appearing in multi‐digit numeric tokens.

    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
    {
    -2.52
    —
    -2.39
    -
    -2.38
    A
    -2.33
     the
    -2.33
    in
    -2.25
    }
    -2.16
    ….
    -2.09
    is
    -2.09
    r
    -2.06
    POSITIVE LOGITS
    橚
    2.69
    𐀀
    2.69
    𓁹
    2.63
    ⬈
    2.59
    geſ
    2.59
    鋱
    2.55
    ᯾
    2.52
     ſou
    2.52
    ⎆
    2.50
    螽
    2.48
    Activations Density 0.009%

    No Known Activations