© 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. 233006
    Prev
    Next
    INDEX
    Explanations

    craving; or craving

    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
     Kommission
    0.47
     masing
    0.46
     Vi
    0.46
    setContentType
    0.45
    ながら
    0.44
     Mew
    0.43
     Commission
    0.42
    S
    0.40
     Bay
    0.40
     INT
    0.40
    POSITIVE LOGITS
     زيد
    0.54
     захо
    0.53
    elve
    0.51
    ем
    0.50
    operateur
    0.50
     जून
    0.49
     LOTRAchievement
    0.49
     ác
    0.48
     كرد
    0.47
    疸
    0.46
    Activations Density 0.000%

    No Known Activations