© 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. 200277
    Prev
    Next
    INDEX
    Explanations

    applicable policies

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

    meaning of life, funny, music

    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
    ών
    0.47
    ານ
    0.45
    كي
    0.45
    ギリス
    0.45
     oplossing
    0.45
     bonnes
    0.45
     filesystem
    0.45
    푐
    0.43
    禳
    0.43
    ом
    0.42
    POSITIVE LOGITS
    employment
    0.51
    iend
    0.49
    thing
    0.48
    associated
    0.47
    rocket
    0.47
    the
    0.46
    TAG
    0.46
    gend
    0.46
    sett
    0.45
    our
    0.45
    Activations Density 0.000%

    No Known Activations