© 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. 98452
    Prev
    Next
    INDEX
    Explanations

    common continuations

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

    own

    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
    -
    0.57
     mounting
    0.51
     drawing
    0.50
     branding
    0.49
     terrorism
    0.48
     cooling
    0.47
     aryl
    0.47
     cogeneration
    0.47
     overheating
    0.47
     thermal
    0.46
    POSITIVE LOGITS
     Biblioteca
    0.57
    sa
    0.56
    s
    0.53
    ⸙
    0.50
     Rfc
    0.48
    太太
    0.48
    wght
    0.48
    nH
    0.47
    attin
    0.47
    跛
    0.46
    Activations Density 0.000%

    No Known Activations