© 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. 178646
    Prev
    Next
    INDEX
    Explanations

    German Spitz

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

    language and technical terms

    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
     божомол
    0.47
    酈
    0.47
     массы
    0.46
    "
    0.46
     absorbed
    0.44
     উত্তম
    0.43
     पढ़
    0.43
    fortunate
    0.43
    ///
    0.43
    サリー
    0.43
    POSITIVE LOGITS
     Ske
    0.47
     Jas
    0.44
     Dok
    0.44
    코드
    0.44
     Wail
    0.44
    gleich
    0.44
     Nath
    0.44
    urgia
    0.44
     Gleich
    0.42
    قة
    0.42
    Activations Density 0.001%

    No Known Activations