© 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. 40-GEMMASCOPE-2-RES-262K
    7. 191248
    Prev
    Next
    INDEX
    Explanations

    divulge

    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_40_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
     "))
    0.44
    തു
    0.39
     """)
    0.39
    sister
    0.39
     』
    0.39
     ").
    0.38
    tam
    0.37
    Tam
    0.37
    長い
    0.37
    ويض
    0.37
    POSITIVE LOGITS
     Π
    0.44
     구성
    0.41
    ();}
    0.41
     수를
    0.41
     `
    0.41
     την
    0.40
     mantra
    0.39
     fact
    0.39
     בדי
    0.39
     expl
    0.38
    Activations Density 0.002%

    No Known Activations