© 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. 244954
    Prev
    Next
    INDEX
    Explanations

    location or area 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
     vingt
    0.48
     Beschreibung
    0.48
     Verv
    0.48
     minuten
    0.47
     ৪
    0.47
     Entsche
    0.46
     Gł
    0.46
     gefragt
    0.46
     ebenfalls
    0.46
     ალ
    0.46
    POSITIVE LOGITS
    ।
    0.47
    ardust
    0.47
    ampur
    0.47
    users
    0.46
    soap
    0.45
    Keb
    0.44
    appeal
    0.44
    water
    0.44
    য়ার
    0.44
    NSNumber
    0.44
    Activations Density 0.001%

    No Known Activations