© 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. 71574
    Prev
    Next
    INDEX
    Explanations

    opinions and views

    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_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
    étaires
    -1.94
    獃
    -1.89
     鸡
    -1.77
    𖧵
    -1.77
    徘
    -1.76
    ान
    -1.75
    🕗
    -1.73
    редиенты
    -1.73
     kämp
    -1.70
    orodos
    -1.70
    POSITIVE LOGITS
    f
    2.25
    0
    2.22
    9
    2.06
    3
    2.06
    2
    2.03
    6
    2.00
    8
    1.97
    7
    1.92
    5
    1.88
    s
    1.84
    Activations Density 0.014%

    No Known Activations