© 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. 9626
    Prev
    Next
    INDEX
    Explanations

    Eva and evasion

    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
    S
    -3.31
    B
    -2.89
    1
    -2.75
    en
    -2.63
    骉
    -2.59
    end
    -2.58
     alcuni
    -2.56
    ين
    -2.47
    3
    -2.39
    H
    -2.38
    POSITIVE LOGITS
    To
    2.39
    琹
    2.30
    蒗
    2.20
    ︓
    2.16
     entendu
    2.14
    ‣
    2.13
    錞
    2.06
     seleccionado
    2.02
    懦
    2.00
    囿
    1.99
    Activations Density 0.001%

    No Known Activations