© 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. 172978
    Prev
    Next
    INDEX
    Explanations

    community activation

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

    historical context

    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
     phenomena
    0.51
    顕
    0.50
    versions
    0.47
    örter
    0.46
    scriptions
    0.45
     preferably
    0.44
     희
    0.44
    binary
    0.43
    apons
    0.43
    cylinder
    0.43
    POSITIVE LOGITS
    يت
    0.70
    يس
    0.56
    ات
    0.55
    بي
    0.52
     சிலையின்
    0.52
    تب
    0.52
    تك
    0.52
     xương
    0.52
    وي
    0.51
    ك
    0.51
    Activations Density 0.000%

    No Known Activations