© 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. 16917
    Prev
    Next
    INDEX
    Explanations

    parentheses and commas

    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
    -/
    0.38
     Sac
    0.36
     Послед
    0.36
    entar
    0.36
     Sementara
    0.35
    langen
    0.35
    -[
    0.35
    -(\
    0.35
    lös
    0.34
     Кроме
    0.34
    POSITIVE LOGITS
     statistically
    0.38
     firstly
    0.38
     scientifically
    0.38
     vrlo
    0.37
     concurring
    0.37
    ᱕
    0.36
     somewhat
    0.36
    치
    0.36
     વા
    0.35
     experimentally
    0.35
    Activations Density 0.045%

    No Known Activations