© 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. 228324
    Prev
    Next
    INDEX
    Explanations

    prefixes, identifiers, and specific nouns

    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
    顶
    0.61
    ને
    0.54
    なる
    0.44
    Budget
    0.42
    தலாக
    0.42
    пут
    0.41
    まだまだ
    0.40
    ia
    0.40
     তথ
    0.40
    全然
    0.40
    POSITIVE LOGITS
     betta
    0.54
     dritte
    0.54
     erste
    0.49
     ਲ
    0.49
     katth
    0.48
     isset
    0.48
    錳
    0.47
     textbox
    0.46
     強
    0.46
     wechseln
    0.45
    Activations Density 0.000%

    No Known Activations