© 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. 210935
    Prev
    Next
    INDEX
    Explanations

    software beta testing

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

    language understanding

    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
    в
    0.49
    iter
    0.49
    н
    0.48
    na
    0.47
    ي
    0.45
     Teilnahme
    0.44
     negras
    0.44
    u
    0.44
     dialects
    0.44
    ritte
    0.43
    POSITIVE LOGITS
    成長
    0.52
     traduire
    0.47
    苇
    0.45
    WithPath
    0.45
    成长
    0.45
     다르
    0.45
     Scul
    0.44
    Glad
    0.44
    イング
    0.44
     quals
    0.43
    Activations Density 0.000%

    No Known Activations