© 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. 129169
    Prev
    Next
    INDEX
    Explanations

    adult tooth loss

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

    short hung man

    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
    wirken
    0.49
    zal
    0.46
    )+
    0.45
    olk
    0.44
    즐
    0.44
    समझ
    0.43
    ningen
    0.41
    polyfill
    0.41
    +$
    0.40
     Jubilee
    0.40
    POSITIVE LOGITS
    の時間
    0.55
     ና
    0.52
    フィ
    0.52
     amico
    0.52
     aquí
    0.51
     einst
    0.51
     amici
    0.50
     rispett
    0.50
     primero
    0.50
     અહીં
    0.49
    Activations Density 0.000%

    No Known Activations