© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 10466
    Prev
    Next
    INDEX
    Explanations

    code snippets and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ialah
    0.45
     adalah
    0.40
     แล
    0.39
     forwarding
    0.38
    \|=
    0.38
     キー
    0.37
    ]#
    0.37
    额外
    0.36
    Autor
    0.36
     제시
    0.36
    POSITIVE LOGITS
    .`);
    0.45
    .`
    0.45
    ဖြင့်
    0.42
    alley
    0.41
    ချုပ်
    0.40
     απε
    0.39
     να
    0.38
    `);
    0.38
    addPreferredGap
    0.37
    ρθ
    0.37
    Activations Density 0.042%

    No Known Activations