© 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. 129535
    Prev
    Next
    INDEX
    Explanations

    selected cell

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

    pronoun + following verb/adjective

    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
    ศรี
    0.56
    赸
    0.49
    ן
    0.47
    חיל
    0.46
    จิต
    0.45
    URNIZ
    0.45
    น
    0.44
    شہ
    0.43
     fals
    0.43
    敂
    0.42
    POSITIVE LOGITS
     त्यानुसार
    0.49
     ügy
    0.46
     pâle
    0.46
    osti
    0.45
    odore
    0.45
    of
    0.44
    ন্ডি
    0.44
    ellar
    0.42
     vagy
    0.42
     év
    0.42
    Activations Density 0.000%

    No Known Activations