© 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. 45158
    Prev
    Next
    INDEX
    Explanations

    system neutral

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

    discrepancies or solutions

    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
     cross
    0.48
     transnational
    0.46
     manifesto
    0.45
     Stranger
    0.44
    '
    0.44
     Trans
    0.43
     Pen
    0.43
     Tessa
    0.43
     I
    0.42
     reveal
    0.42
    POSITIVE LOGITS
    اردوش
    0.47
    getMax
    0.44
    cparam
    0.44
     لیګ
    0.44
    ்கலை
    0.43
    ‌്
    0.43
    সঙ্গ
    0.43
     लगाएंगे
    0.43
    健全
    0.42
    軽減
    0.42
    Activations Density 0.000%

    No Known Activations