© 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. 12049
    Prev
    Next
    INDEX
    Explanations

    proper names after punctuation

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

    percentage of

    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
    ósz
    0.37
    ôle
    0.37
    的面
    0.37
     movimenti
    0.37
    amanho
    0.37
    衅
    0.36
    ildet
    0.36
    omy
    0.35
    emment
    0.35
    ższy
    0.35
    POSITIVE LOGITS
     века
    0.42
     которая
    0.42
     ника
    0.42
     integrada
    0.42
     declinations
    0.41
     Declined
    0.39
    RELATED
    0.39
     яка
    0.37
     Сури
    0.37
    }([
    0.37
    Activations Density 0.013%

    No Known Activations