© 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. 76297
    Prev
    Next
    INDEX
    Explanations

    put, conclude, negotiate

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

    phys. descriptions, manufacturing, or 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
     cell
    0.62
    0.51
     panel
    0.48
     slide
    0.46
     horror
    0.46
     slides
    0.46
     plea
    0.46
     recall
    0.45
     $.
    0.45
     being
    0.45
    POSITIVE LOGITS
    <unused382>
    0.55
     功能
    0.52
    Phương
    0.52
    ódigo
    0.51
    <unused224>
    0.51
    ഭാഗ
    0.50
    <unused654>
    0.50
    <unused711>
    0.50
     എന്ത
    0.49
    WithFieldContext
    0.49
    Activations Density 0.000%

    No Known Activations