Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 44319
    Prev
    Next
    INDEX
    Explanations

    gathering/getting labels

    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
    good
    0.46
    ment
    0.44
    ↵↵↵↵
    0.43
     producers
    0.43
     latino
    0.43
    well
    0.42
    osan
    0.42
     
    0.42
    -
    0.42
    ↵↵
    0.42
    POSITIVE LOGITS
     Misalnya
    0.49
    SETS
    0.49
     график
    0.47
    AutoStabilise
    0.47
    ➠
    0.47
    Button
    0.47
     দার্শন
    0.47
    𒄀
    0.47
    聶
    0.47
    Lc
    0.47
    Activations Density 0.003%

    No Known Activations