© 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. 165521
    Prev
    Next
    INDEX
    Explanations

    candy, father, current

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

    credit advertisements

    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
    ge
    0.47
    li
    0.47
    cyl
    0.46
     immediate
    0.46
    t
    0.45
    pas
    0.44
    str
    0.44
    rea
    0.44
     enzyme
    0.44
     multival
    0.44
    POSITIVE LOGITS
    ｱ
    0.52
     psicología
    0.48
     esperado
    0.48
    괌
    0.48
     Cramer
    0.47
    विदा
    0.47
     psicologia
    0.47
     SLE
    0.45
    аль
    0.45
    イッチ
    0.45
    Activations Density 0.002%

    No Known Activations