© 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. 16-GEMMASCOPE-2-RES-262K
    7. 27986
    Prev
    Next
    INDEX
    Explanations

    many followed by a noun

    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_16_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
    вите
    0.59
    ونها
    0.57
    Were
    0.55
     Certains
    0.55
     manches
    0.55
    럏
    0.55
     dingen
    0.55
     pedibusque
    0.55
    цами
    0.54
     titulares
    0.54
    POSITIVE LOGITS
    .
    0.70
     in
    0.67
     עם
    0.63
     an
    0.63
     with
    0.59
     a
    0.59
     &
    0.59
    ång
    0.58
     whenever
    0.57
     .
    0.57
    Activations Density 0.003%

    No Known Activations