© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 163161
    Prev
    Next
    INDEX
    Explanations

    eyeshadow laws editor experience property

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

    listing or structuring ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ビ
    0.50
    ımı
    0.50
    か月
    0.49
    忘れ
    0.48
     вось
    0.48
    ૬
    0.48
     そこ
    0.48
     Kabir
    0.48
     ingeniero
    0.48
    wię
    0.47
    POSITIVE LOGITS
    wal
    0.45
     tret
    0.45
    地址
    0.45
    iner
    0.44
     rspace
    0.43
    T
    0.43
    pletely
    0.43
    abend
    0.42
     Waldo
    0.42
     verb
    0.41
    Activations Density 0.000%

    No Known Activations