© 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. 32658
    Prev
    Next
    INDEX
    Explanations

    present followed by formal nouns

    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
     the
    0.54
    a
    0.52
    the
    0.51
     on
    0.47
    and
    0.47
    h
    0.47
     and
    0.46
     अफेयर्स
    0.46
    ä
    0.46
     Affairs
    0.45
    POSITIVE LOGITS
     musculoskeletal
    0.42
     moment
    0.41
     circunstancias
    0.41
    MSFont
    0.41
    ңуз
    0.41
     esclusivamente
    0.41
    InputChange
    0.40
    식회사
    0.40
     gdyż
    0.40
    િમ
    0.39
    Activations Density 0.003%

    No Known Activations