© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 94539
    Prev
    Next
    INDEX
    Explanations

    prepositions and connectors

    np_acts-logits-general · gemini-2.5-flash-lite

    states and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perceptions
    0.46
    ्ञ
    0.45
     å
    0.43
     aspectos
    0.43
    ڤ
    0.42
     labourers
    0.42
     SMEs
    0.41
     inne
    0.41
     visitantes
    0.41
     états
    0.41
    POSITIVE LOGITS
    াকা
    0.47
    輥
    0.45
    ামিটার
    0.45
    tting
    0.44
     टारगेट
    0.44
    轸
    0.43
    Macro
    0.42
     टॉ
    0.42
    স্টে
    0.42
     পেন
    0.42
    Activations Density 0.002%

    No Known Activations