© 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. 25122
    Prev
    Next
    INDEX
    Explanations

    years, time, year, suite

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

    explaining technical terms

    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
    ików
    0.50
     প্রান্ত
    0.48
    <0x1E>
    0.47
     प्र
    0.46
     możesz
    0.45
     vực
    0.45
     वांछ
    0.45
     न्यूनतम
    0.44
     ഉറ
    0.44
     دہ
    0.44
    POSITIVE LOGITS
    鲔
    0.46
    anvil
    0.45
    cription
    0.45
    ostridium
    0.44
     brachial
    0.43
    AR
    0.42
    winged
    0.42
    AL
    0.42
     Ir
    0.42
    RG
    0.42
    Activations Density 0.000%

    No Known Activations