© 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-262K
    7. 40826
    Prev
    Next
    INDEX
    Explanations

    you followed by a word

    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_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
    秇
    0.45
     Kotlin
    0.44
     হাজার
    0.42
    itation
    0.41
    eniem
    0.41
    พ
    0.41
     tray
    0.40
    verte
    0.40
    🥫
    0.40
    ilibr
    0.39
    POSITIVE LOGITS
     ведет
    0.43
    ಕ್ಕು
    0.41
    看
    0.40
     stormed
    0.40
    chooser
    0.40
    デメリット
    0.40
    рис
    0.39
    憎
    0.39
    晶
    0.38
    িয়া
    0.38
    Activations Density 0.007%

    No Known Activations