© 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. 117243
    Prev
    Next
    INDEX
    Explanations

    He reported speech

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

    He and his statements

    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
     mentioning
    0.50
    dragging
    0.47
    TEE
    0.46
    د
    0.46
    dip
    0.44
    nails
    0.44
    說是
    0.43
    talking
    0.43
    tki
    0.43
     uñas
    0.42
    POSITIVE LOGITS
    0.47
    eding
    0.46
     wholly
    0.46
    ="
    0.45
    во
    0.41
     echoed
    0.41
     piek
    0.41
    哋
    0.41
     stesso
    0.41
    ",
    0.41
    Activations Density 0.015%

    No Known Activations