© 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. 54560
    Prev
    Next
    INDEX
    Explanations

    USB, child, collection

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

    data collection and preprocessing

    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
    лект
    0.47
     busted
    0.46
     monotonic
    0.45
    蒙
    0.45
    Montgomery
    0.45
     supporter
    0.43
    MEX
    0.43
     preacher
    0.42
    K
    0.42
     stimulation
    0.42
    POSITIVE LOGITS
    ants
    0.59
     週
    0.52
     Objekt
    0.51
    yl
    0.50
    genommen
    0.50
    ab
    0.50
    aker
    0.48
     ਟ
    0.48
    unt
    0.48
     單
    0.48
    Activations Density 0.000%

    No Known Activations