© 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. 103533
    Prev
    Next
    INDEX
    Explanations

    specific entities and their relationships

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

    decisions or consequences

    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
    Negative Logits
    ЛИ
    0.48
    ENER
    0.48
    ICAN
    0.46
    ADOS
    0.46
     رئيس
    0.46
    ANA
    0.45
    ☠
    0.45
    INES
    0.45
     காலநிலை
    0.45
    ান্ডের
    0.45
    POSITIVE LOGITS
     nakon
    0.59
     kontek
    0.56
     a
    0.55
     setelah
    0.54
     bagus
    0.52
     Knows
    0.50
     efter
    0.49
     il
    0.49
     après
    0.47
     Holds
    0.47
    Activations Density 0.001%

    No Known Activations