© 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. 229048
    Prev
    Next
    INDEX
    Explanations

    parts of descriptions

    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
    1
    0.54
    5
    0.52
     Barn
    0.50
    ეს
    0.49
    9
    0.48
     Stage
    0.48
    인지
    0.47
    ad
    0.46
    7
    0.46
     Stephenson
    0.46
    POSITIVE LOGITS
     beliebt
    0.49
     analyte
    0.48
     ү
    0.47
    NULL
    0.46
     triángulos
    0.46
     وخت
    0.45
     vértice
    0.44
    បញ្
    0.44
    gradient
    0.44
     esprim
    0.43
    Activations Density 0.001%

    No Known Activations