© 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. 26017
    Prev
    Next
    INDEX
    Explanations

    rehabilitation, delete, belt, insulation, cinch

    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
    вно
    0.44
    薛
    0.43
    こと
    0.41
     सोर्स
    0.40
     we
    0.40
     résult
    0.40
     membre
    0.40
     लड़
    0.39
    任命
    0.39
    произ
    0.38
    POSITIVE LOGITS
    |");
    0.45
    anno
    0.44
    alinga
    0.42
     పాల
    0.42
    uris
    0.42
    akam
    0.42
    skyscraper
    0.41
    haha
    0.41
    bridge
    0.41
     床
    0.41
    Activations Density 0.000%

    No Known Activations