© 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. 37262
    Prev
    Next
    INDEX
    Explanations

    turn of events

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

    instructional phrases

    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
    hut
    0.48
    เต
    0.47
     ያስ
    0.47
    ส
    0.46
    जिला
    0.46
    end
    0.44
     забо
    0.43
    id
    0.42
    妮
    0.42
    cd
    0.42
    POSITIVE LOGITS
     esteja
    0.51
     desiderio
    0.48
     exist
    0.48
     stesse
    0.48
     esetén
    0.48
     variabili
    0.47
     motivations
    0.47
     weiterhin
    0.47
     están
    0.46
     Fukushima
    0.46
    Activations Density 0.000%

    No Known Activations