© 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. 150158
    Prev
    Next
    INDEX
    Explanations

    prerequisites and considerations

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

    data, applications, configurations

    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
    hombre
    0.45
     Hombre
    0.44
     nationals
    0.41
    ᱞ
    0.40
    entre
    0.40
     ventures
    0.39
     clube
    0.39
    gov
    0.39
    ುತ್ತವೆ
    0.39
     compatriots
    0.39
    POSITIVE LOGITS
    𝓶
    0.54
    𝒙
    0.52
     Prerequisites
    0.50
     گیری
    0.49
     작업을
    0.49
     శరీర
    0.49
    𝒚
    0.49
     Considerations
    0.48
     элемента
    0.47
     必要
    0.46
    Activations Density 0.000%

    No Known Activations