© 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. 19857
    Prev
    Next
    INDEX
    Explanations

    history, encompasses, contacted

    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
     normative
    0.47
     Vocational
    0.44
     conscientious
    0.44
    挪
    0.42
     vocational
    0.40
     lawful
    0.40
     voix
    0.40
    刘
    0.39
    权力
    0.39
     vaccination
    0.39
    POSITIVE LOGITS
    Merge
    0.49
     zde
    0.48
     tenements
    0.47
    <unused15>
    0.46
     Bhos
    0.46
    Make
    0.46
     Cavs
    0.45
    Circles
    0.45
    Bootstrap
    0.44
     formada
    0.44
    Activations Density 0.024%

    No Known Activations