© 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-262K
    7. 41999
    Prev
    Next
    INDEX
    Explanations

    programming include directives

    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_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
    channel
    0.50
    σ
    0.48
     δρα
    0.47
    Watts
    0.44
    letter
    0.43
     channel
    0.43
    確率
    0.43
    Tick
    0.42
    Channel
    0.41
    драт
    0.41
    POSITIVE LOGITS
     peralatan
    0.53
     تجهیز
    0.47
     penghargaan
    0.45
     alberga
    0.45
     pesantren
    0.45
    秣
    0.45
     entregar
    0.44
     abrigo
    0.44
     encamp
    0.44
    amentos
    0.43
    Activations Density 0.007%

    No Known Activations