© 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. 124806
    Prev
    Next
    INDEX
    Explanations

    website navigation actions and links

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

    words forming 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
    endim
    0.52
    uak
    0.50
    calf
    0.48
    브
    0.48
    iya
    0.47
     quin
    0.46
    ave
    0.46
    ikal
    0.46
    umum
    0.46
    uah
    0.46
    POSITIVE LOGITS
     excursions
    0.53
    Zona
    0.49
    ر
    0.49
    赵
    0.48
    رق
    0.48
     Tail
    0.47
     Throat
    0.46
     hurling
    0.46
    Tail
    0.44
    Mara
    0.44
    Activations Density 0.000%

    No Known Activations