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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 48790
    Prev
    Next
    INDEX
    Explanations

    recommendation letters and website banners

    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
    avacan
    0.49
    ඓ
    0.47
    다
    0.46
    티
    0.46
    数が
    0.46
    یر
    0.46
    ப்பான
    0.45
    ტი
    0.45
    푅
    0.44
    울
    0.44
    POSITIVE LOGITS
     Aug
    0.47
     be
    0.47
     व
    0.45
    me
    0.45
    men
    0.45
    ↵
    0.44
    be
    0.44
     ने
    0.44
    ridge
    0.43
     caused
    0.43
    Activations Density 0.003%

    No Known Activations