© 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. 105226
    Prev
    Next
    INDEX
    Explanations

    time units and informational words

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

    code and technical terms

    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
    一
    0.55
     dedos
    0.49
    ت
    0.48
     fingers
    0.47
     peper
    0.47
     touchpad
    0.47
     neodymium
    0.47
    三個
    0.46
    鳧
    0.46
     peat
    0.46
    POSITIVE LOGITS
    Naturally
    0.52
    ных
    0.51
    ses
    0.50
    gü
    0.50
    hôpital
    0.48
    सेस
    0.47
    purs
    0.47
    spent
    0.47
    rines
    0.46
    criminals
    0.46
    Activations Density 0.000%

    No Known Activations