© 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. 123248
    Prev
    Next
    INDEX
    Explanations

    TP53 mutations

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

    BMW, Mercedes-Benz, angular designs

    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
     Buckeye
    0.40
     Reuben
    0.40
     للد
    0.39
    ства
    0.39
     scout
    0.38
     scouting
    0.38
     للإ
    0.38
    鍊
    0.38
    privileged
    0.38
     لطف
    0.37
    POSITIVE LOGITS
    preliquidacion
    0.45
     моро
    0.42
     pê
    0.41
     perturbed
    0.40
    onbury
    0.40
    Orlando
    0.39
    แมนเชสเตอร์ซิตี
    0.39
    戴
    0.39
    CoO
    0.39
    Dame
    0.38
    Activations Density 0.023%

    No Known Activations