© 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. 3382
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

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

    file paths and resource links

    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
     الطعام
    0.41
    ن
    0.39
     femei
    0.38
    OMBRE
    0.38
    onycha
    0.37
    طاء
    0.37
     diathermy
    0.37
     إذا
    0.36
     quelqu
    0.35
     الشعر
    0.35
    POSITIVE LOGITS
     ../
    0.55
    https
    0.53
     https
    0.52
     the
    0.50
     '../
    0.46
     "../
    0.46
     http
    0.45
    http
    0.45
     www
    0.44
     '@/
    0.44
    Activations Density 0.018%

    No Known Activations