© 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. 224370
    Prev
    Next
    INDEX
    Explanations

    family and offspring

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

    // Prepend

    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
    ورك
    0.50
    כנס
    0.46
     soliciting
    0.43
    饋
    0.43
     stirrer
    0.43
    readthedocs
    0.42
     hangover
    0.42
    まり
    0.42
    園
    0.42
     brewery
    0.40
    POSITIVE LOGITS
     Cauchy
    0.48
     해당
    0.46
     countably
    0.46
     аў
    0.46
    Likewise
    0.46
     lLoginID
    0.45
     Mannschaften
    0.44
    Accum
    0.44
     якая
    0.44
     산
    0.44
    Activations Density 0.002%

    No Known Activations