© 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. 71492
    Prev
    Next
    INDEX
    Explanations

    life story summaries

    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
    िर
    0.52
    ן
    0.48
    ानी
    0.47
    дан
    0.46
    ри
    0.45
    ान्
    0.45
    Colonne
    0.45
    ῎
    0.44
    𝐬
    0.43
    ص
    0.43
    POSITIVE LOGITS
     shoreline
    0.53
     orchards
    0.50
     places
    0.48
     regularly
    0.48
     associates
    0.47
     airports
    0.46
     associated
    0.46
     complement
    0.46
    uto
    0.45
     stores
    0.45
    Activations Density 0.007%

    No Known Activations