© 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. 240581
    Prev
    Next
    INDEX
    Explanations

    protection, advice, stroke, furniture

    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
    subtype
    0.55
    ეგ
    0.50
    etary
    0.49
    ああ
    0.48
    қ
    0.48
    fieldname
    0.47
     creatively
    0.47
    idirectional
    0.46
     habitat
    0.46
    Placeholder
    0.46
    POSITIVE LOGITS
     sez
    0.45
    荞
    0.44
     URI
    0.43
     किरा
    0.42
     fornece
    0.42
    供给
    0.40
    猕
    0.40
     circun
    0.40
     augmente
    0.40
     津
    0.40
    Activations Density 0.000%

    No Known Activations