© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 169490
    Prev
    Next
    INDEX
    Explanations

    legislative beat; limitation on; daily on; June holiday

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

    observations and development

    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
    ність
    0.52
     дороже
    0.52
    
    0.52
    ⓝ
    0.49
    เพราะ
    0.48
     équipe
    0.48
    暘
    0.47
     Chew
    0.47
    ن
    0.47
    ני
    0.47
    POSITIVE LOGITS
     dismissed
    0.49
    ond
    0.47
     glazed
    0.47
    err
    0.46
    are
    0.46
    pre
    0.45
    omeric
    0.44
    amburg
    0.44
     pre
    0.43
    urred
    0.43
    Activations Density 0.000%

    No Known Activations