© 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. 37272
    Prev
    Next
    INDEX
    Explanations

    summaries, assessments, understanding

    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
    {
    0.57
    a
    0.55
    Kost
    0.50
    Supported
    0.48
    Il
    0.46
    Spare
    0.46
     Campeonato
    0.46
    эк
    0.46
    Deze
    0.46
    Ao
    0.45
    POSITIVE LOGITS
     lacer
    0.51
     спів
    0.48
     ဖ
    0.48
     fallout
    0.45
     bait
    0.45
     heavens
    0.44
     linguaggio
    0.44
     blossomed
    0.44
     optically
    0.43
     нака
    0.43
    Activations Density 0.000%

    No Known Activations