© 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. 30349
    Prev
    Next
    INDEX
    Explanations

    provinceDesign

    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
    ставля
    0.49
    thats
    0.45
    othes
    0.45
    త్వ
    0.45
    Bài
    0.45
    :")
    0.45
    creen
    0.45
    ياء
    0.44
    _______________
    0.44
    Tuesday
    0.44
    POSITIVE LOGITS
     FOR
    0.54
     OMG
    0.49
     IF
    0.48
     Despite
    0.45
     for
    0.43
     SH
    0.43
     WAS
    0.43
     Forst
    0.43
     ADA
    0.42
     Although
    0.42
    Activations Density 0.003%

    No Known Activations