© 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. 40-GEMMASCOPE-2-RES-262K
    7. 832
    Prev
    Next
    INDEX
    Explanations

    percentile dice

    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_40_width_262k_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
     grij
    0.43
    有利于
    0.42
    {
    0.42
     fiscale
    0.42
     consentement
    0.42
     sociale
    0.40
     prestations
    0.40
     resumes
    0.40
    Automat
    0.39
    ?:
    0.38
    POSITIVE LOGITS
     by
    0.46
    撓
    0.45
     cellar
    0.43
     relieving
    0.43
     ʼ
    0.43
     peculiarly
    0.42
     nyata
    0.42
    erd
    0.41
     Н
    0.41
     vineyard
    0.41
    Activations Density 0.000%

    No Known Activations