© 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. 247334
    Prev
    Next
    INDEX
    Explanations

    water element, knocking anyone, attending church

    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
     confronts
    0.45
    ☠
    0.44
    살
    0.41
    国土
    0.40
    যুব
    0.40
     мастеров
    0.39
    土地
    0.39
     губернатора
    0.38
    鄂
    0.38
    కి
    0.38
    POSITIVE LOGITS
     indicating
    0.47
     espes
    0.46
     Academia
    0.46
     acara
    0.46
     recevoir
    0.45
     eset
    0.45
     antaranya
    0.44
    有一个
    0.44
     estoy
    0.43
     Essen
    0.43
    Activations Density 0.002%

    No Known Activations