© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 21941
    Prev
    Next
    INDEX
    Explanations

    thinking about or of

    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
    dresser
    0.36
    Think
    0.35
    機会
    0.35
     $[\
    0.34
     înainte
    0.34
    $[\
    0.34
     hypertro
    0.34
    $[
    0.34
    aghe
    0.33
    $(\
    0.33
    POSITIVE LOGITS
    স্তাফিজ
    0.45
     Hoping
    0.45
     Either
    0.44
     soit
    0.42
     capping
    0.42
     wondering
    0.42
     ಮೋ
    0.41
     VIAF
    0.41
     Casting
    0.41
     aloud
    0.41
    Activations Density 0.003%

    No Known Activations