© 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. 191303
    Prev
    Next
    INDEX
    Explanations

    AI style

    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
     rhetorical
    0.38
    ﺘ
    0.38
    図
    0.37
     privileged
    0.36
     `:
    0.36
    ދ
    0.36
     приви
    0.36
     Subscription
    0.35
     Subscriber
    0.35
    recycl
    0.34
    POSITIVE LOGITS
     aren
    0.44
    િવસ
    0.41
    Printing
    0.41
     pushing
    0.40
    녕하십니까
    0.40
     Likely
    0.39
    荡
    0.39
     Must
    0.38
     isn
    0.38
    antaranya
    0.37
    Activations Density 0.000%

    No Known Activations