© 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. 122051
    Prev
    Next
    INDEX
    Explanations

    reduction, court, Allie, promise, April

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

    explaining rationale and motivation

    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
    associate
    0.51
     técnicos
    0.50
    medskip
    0.49
     tecnici
    0.47
    -\
    0.46
    W
    0.45
    circ
    0.45
    ´
    0.44
    <?
    0.44
    ľ
    0.44
    POSITIVE LOGITS
    यन
    0.50
    剡
    0.49
     সিরিজ
    0.49
    loride
    0.48
    鐟
    0.48
     कुर
    0.47
     konfl
    0.46
    涳
    0.46
    ेश्च
    0.45
    ालय
    0.45
    Activations Density 0.001%

    No Known Activations