© 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. 162592
    Prev
    Next
    INDEX
    Explanations

    safety record, creating titles

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

    code and technical documentation

    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
     dù
    0.59
     بأن
    0.50
     rift
    0.50
     budou
    0.50
     oliv
    0.48
    జ్
    0.48
    :
    0.48
    ("|
    0.48
    теры
    0.46
     トート
    0.46
    POSITIVE LOGITS
    did
    0.49
    ून
    0.48
    ayani
    0.46
    don
    0.45
    工作中
    0.44
    e
    0.44
    also
    0.43
    लेशन
    0.43
    inicio
    0.42
     paranoid
    0.42
    Activations Density 0.000%

    No Known Activations