© 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. 238459
    Prev
    Next
    INDEX
    Explanations

    services nor cup final slot fit

    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
    ="@+
    0.50
    า
    0.50
     অমন
    0.48
     मांगने
    0.47
     열
    0.46
     ಯು
    0.46
     당
    0.46
     רו
    0.45
     과학
    0.45
    arsanız
    0.45
    POSITIVE LOGITS
     فترة
    0.55
     enjo
    0.48
     comum
    0.47
     hafa
    0.47
     audit
    0.46
     attaché
    0.46
    ㄠ
    0.46
     dá
    0.46
     czasie
    0.46
     entren
    0.46
    Activations Density 0.000%

    No Known Activations