© 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. 29548
    Prev
    Next
    INDEX
    Explanations

    defining Python functions or code blocks

    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
     Morley
    0.45
     Adler
    0.40
     bet
    0.39
     coke
    0.39
    圧力
    0.39
    貴
    0.39
     heatmap
    0.38
     Spar
    0.38
     Molly
    0.38
    _{+}
    0.37
    POSITIVE LOGITS
    Respond
    0.40
    withId
    0.39
     register
    0.39
    訶
    0.38
     regist
    0.38
     হইলে
    0.36
    responds
    0.36
    iseite
    0.35
    irió
    0.35
    if
    0.35
    Activations Density 0.002%

    No Known Activations