© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 361
    Prev
    Next
    INDEX
    Explanations

    virtual connect program

    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
     very
    0.30
     interpolation
    0.29
     horribly
    0.29
     Very
    0.27
     r
    0.26
     Herrn
    0.25
     terribly
    0.25
     Pseudo
    0.25
     '
    0.25
     unusually
    0.25
    POSITIVE LOGITS
     partnering
    0.33
     прибыли
    0.31
    Poppins
    0.31
     reimag
    0.31
     платформа
    0.31
    ⼒
    0.30
     plateforme
    0.30
     partenaire
    0.30
     компания
    0.30
     партнер
    0.30
    Activations Density 0.206%

    No Known Activations