© 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. 200162
    Prev
    Next
    INDEX
    Explanations

    descriptive suffixes and following words

    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
     SUVs
    0.48
    သွ
    0.48
     regret
    0.47
     பெ
    0.45
     Rece
    0.45
     Benz
    0.45
    ¹,
    0.45
     intran
    0.44
     ischemic
    0.43
     Lexus
    0.42
    POSITIVE LOGITS
    раб
    0.48
    َة
    0.47
    Constraints
    0.44
    o
    0.44
    টিত
    0.44
    AMINATION
    0.44
    ⚒
    0.44
    unate
    0.43
    USTOM
    0.43
    URIS
    0.42
    Activations Density 0.003%

    No Known Activations