© 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. 41999
    Prev
    Next
    INDEX
    Explanations

    string and memory limits

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

    programming include directives

    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
    σ
    0.55
     Gazette
    0.47
    ш
    0.45
    ल
    0.45
    ounter
    0.44
    q
    0.44
    τ
    0.44
    確率
    0.44
     δρα
    0.43
    心
    0.43
    POSITIVE LOGITS
     abrigo
    0.54
     alberga
    0.49
     peralatan
    0.49
     Sistemas
    0.48
     cabel
    0.48
     پوش
    0.47
     novembre
    0.46
     tytu
    0.46
     تجهیز
    0.46
     붙
    0.44
    Activations Density 0.000%

    No Known Activations