© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 202555
    Prev
    Next
    INDEX
    Explanations

    recycled throughout

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

    OpenAI Agent

    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
     ނ
    0.50
     نیند
    0.49
    waitForIdleSync
    0.47
     پڑے
    0.47
    marshalN
    0.46
     හො
    0.46
    參数
    0.46
     harsher
    0.46
    >());
    0.45
     cinci
    0.45
    POSITIVE LOGITS
    م
    0.55
     At
    0.53
    ك
    0.52
    كان
    0.51
     Obat
    0.50
    HE
    0.50
     Osman
    0.50
     HA
    0.50
    HA
    0.49
     Genes
    0.48
    Activations Density 0.001%

    No Known Activations