© 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. 148054
    Prev
    Next
    INDEX
    Explanations

    linking words and subsequent nouns

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

    fraudulent purchases or captive access

    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
    護
    0.54
    variants
    0.48
    server
    0.48
    連接
    0.46
    雞
    0.46
    厛
    0.46
    和其他
    0.46
    壽
    0.45
    𝗌
    0.44
    營
    0.44
    POSITIVE LOGITS
     pienso
    0.48
     explica
    0.45
     colombiano
    0.44
     Why
    0.44
     Filho
    0.43
     Inggris
    0.43
     menit
    0.42
     Explain
    0.42
    <0xB2>
    0.42
    urnama
    0.42
    Activations Density 0.001%

    No Known Activations