© 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. 34788
    Prev
    Next
    INDEX
    Explanations

    technical keywords and descriptions

    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
     chem
    0.52
    燁
    0.46
     brewer
    0.45
     limitation
    0.45
     BSE
    0.44
     premise
    0.44
    醇
    0.44
    营
    0.43
     temps
    0.43
     brief
    0.43
    POSITIVE LOGITS
    Neutral
    0.49
    सपने
    0.47
    Throttle
    0.47
    gün
    0.46
    Philos
    0.46
    Ard
    0.46
    ském
    0.45
    M
    0.45
    lensFlare
    0.44
    Ar
    0.44
    Activations Density 0.005%

    No Known Activations