© 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. 134855
    Prev
    Next
    INDEX
    Explanations

    dark eye

    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
    ப்புக்
    0.48
    ，
    0.46
    லா
    0.43
     gahet
    0.42
    ウィン
    0.42
     を
    0.42
    人類
    0.42
    ─
    0.42
    ，「
    0.41
     Nong
    0.41
    POSITIVE LOGITS
     धर
    0.48
    эр
    0.43
    कल
    0.43
    เมตร
    0.43
     տար
    0.42
     configured
    0.42
     textView
    0.42
    urer
    0.42
    arela
    0.42
     decret
    0.41
    Activations Density 0.000%

    No Known Activations