© 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. 181356
    Prev
    Next
    INDEX
    Explanations

    local election cliché

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

    before entering

    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
     Optics
    0.52
     THIRD
    0.45
    พล
    0.43
    Plant
    0.42
    合った
    0.42
    tall
    0.42
    칡
    0.41
    ड़की
    0.41
    ЛО
    0.40
    Worst
    0.40
    POSITIVE LOGITS
    படுத்த
    0.44
     castell
    0.43
    తున్నాయి
    0.43
    网页
    0.43
    కుంటు
    0.43
     reiter
    0.42
    angulo
    0.42
    கிற
    0.41
    市長
    0.41
    టే
    0.41
    Activations Density 0.001%

    No Known Activations