© 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. 228795
    Prev
    Next
    INDEX
    Explanations

    ultimately eliminates or transforms

    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
     Jacksonville
    0.42
     fiscales
    0.41
    其他
    0.41
     Oklahoma
    0.41
     constitu
    0.40
    赛
    0.40
     California
    0.39
    伱
    0.39
     Orange
    0.38
     آتی
    0.38
    POSITIVE LOGITS
     வெளிய
    0.52
     restricts
    0.48
    臨床
    0.48
    iciens
    0.48
    acés
    0.48
    kers
    0.46
    詫
    0.46
    ähler
    0.46
     സര്‍
    0.45
    thers
    0.45
    Activations Density 0.000%

    No Known Activations