© 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. 245166
    Prev
    Next
    INDEX
    Explanations

    limit of

    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
    0.53
    ir
    0.50
     @
    0.49
    en
    0.48
    he
    0.46
     TER
    0.46
    ing
    0.46
    énergie
    0.45
    in
    0.45
    %,
    0.45
    POSITIVE LOGITS
    ток
    0.52
     parcial
    0.47
    iprofloxacin
    0.44
    tabControl
    0.42
    াবার
    0.42
     noviembre
    0.42
    豆腐
    0.42
    ノート
    0.42
    socks
    0.41
     labored
    0.41
    Activations Density 0.000%

    No Known Activations