© 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. 28148
    Prev
    Next
    INDEX
    Explanations

    consume electricity

    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
     tête
    0.43
     umož
    0.41
     crit
    0.40
     يجب
    0.40
    Acetyl
    0.40
    ové
    0.39
    胙
    0.39
     chariot
    0.39
     pivot
    0.38
     Résultats
    0.38
    POSITIVE LOGITS
    наў
    0.47
     its
    0.47
     cyberspace
    0.46
     their
    0.46
    }.
    0.44
     volition
    0.44
     seashore
    0.44
     determinato
    0.44
     praia
    0.44
    キム
    0.43
    Activations Density 0.000%

    No Known Activations