© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 49992
    Prev
    Next
    INDEX
    Explanations

    benchmark, political, grammatically

    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
    अरविंद
    0.46
    لار
    0.42
    Voilà
    0.42
     innumerable
    0.40
    entire
    0.40
     infinitely
    0.40
    <unused320>
    0.40
     traversed
    0.39
    brows
    0.39
    multiply
    0.39
    POSITIVE LOGITS
     ምክ
    0.45
     তম
    0.43
     haven
    0.43
     Answer
    0.42
     Haven
    0.42
     Ask
    0.42
     answer
    0.41
     해결
    0.40
    ▾
    0.40
     Ref
    0.40
    Activations Density 0.003%

    No Known Activations