© 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. 83141
    Prev
    Next
    INDEX
    Explanations

    follow punctuation

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

    format and structure

    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
     stoichiometric
    0.45
     rive
    0.45
     rougeâtre
    0.43
    וד
    0.43
    ื่น
    0.43
     propellant
    0.42
    ike
    0.41
    ư
    0.41
     stoichi
    0.41
     떨어
    0.41
    POSITIVE LOGITS
    Pin
    0.46
    Dieser
    0.46
    negative
    0.45
    rases
    0.44
    lás
    0.44
    वाद
    0.43
    cao
    0.43
    Minimized
    0.41
    bans
    0.41
    Owned
    0.41
    Activations Density 0.000%

    No Known Activations