© 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. 170131
    Prev
    Next
    INDEX
    Explanations

    numbers, foreign words, and subsequent actions

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

    respect their time

    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
     similit
    0.51
    버지
    0.45
     intellig
    0.45
    ்க்கு
    0.44
    )
    0.44
     maks
    0.42
    йи
    0.42
    xe
    0.42
    ã
    0.42
    );
    0.42
    POSITIVE LOGITS
     两
    0.46
    他的
    0.46
     六
    0.45
     休
    0.45
     později
    0.44
     五
    0.44
    بعد
    0.44
     Subsequent
    0.44
     படிப்ப
    0.44
    ونز
    0.43
    Activations Density 0.000%

    No Known Activations