© 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-65K
    7. 36168
    Prev
    Next
    INDEX
    Explanations

    discussing series, projects, sequences, scripts, wells, problems, documents

    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_65k_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
    𝚂
    0.44
     არის
    0.43
    噉
    0.43
    avacanam
    0.43
    ْس
    0.42
     ಸ್ಥಾನ
    0.41
    revenue
    0.41
     Salaries
    0.41
    大量的
    0.41
    ס
    0.41
    POSITIVE LOGITS
    かもしれませんが
    0.45
     (>
    0.44
     resort
    0.44
     prone
    0.41
     peur
    0.41
     verz
    0.40
     mustard
    0.39
     invention
    0.38
     breakup
    0.38
     application
    0.37
    Activations Density 0.130%

    No Known Activations