© 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. 25145
    Prev
    Next
    INDEX
    Explanations

    Databricks, Dolly

    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
     goc
    0.50
    Americans
    0.48
     proposé
    0.48
     contempt
    0.47
     considerazione
    0.47
     whereupon
    0.47
    Ⲗ
    0.47
     girlfriends
    0.46
     heuristics
    0.46
     superiority
    0.45
    POSITIVE LOGITS
    '
    0.46
    0.44
     Fun
    0.43
     Aug
    0.42
     It
    0.40
     Queen
    0.40
    ories
    0.40
    jährige
    0.40
     Hunger
    0.39
     Feeding
    0.39
    Activations Density 0.008%

    No Known Activations