© 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. 113445
    Prev
    Next
    INDEX
    Explanations

    Speech-to-Text correction

    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
     plateforme
    0.51
    に取り組
    0.51
    🩸
    0.50
     nebo
    0.49
     jejich
    0.49
     Geschäftsführer
    0.49
     policial
    0.48
     behov
    0.47
     comienza
    0.47
     perioada
    0.47
    POSITIVE LOGITS
    s
    0.57
    AK
    0.51
     by
    0.48
    AH
    0.48
    tolyl
    0.45
    QK
    0.44
    BrI
    0.44
    AMES
    0.44
    AMG
    0.43
    ARO
    0.42
    Activations Density 0.000%

    No Known Activations