© 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. 107066
    Prev
    Next
    INDEX
    Explanations

    technical documentation

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

    ascii art, diagrams, connections

    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
    א
    0.61
    ק
    0.57
    િ
    0.56
    ิ
    0.55
    }$.
    0.55
    ע
    0.55
    Bitte
    0.54
    س
    0.54
    ብ
    0.53
        
    0.52
    POSITIVE LOGITS
     Official
    0.58
     इससे
    0.57
     by
    0.51
     Fish
    0.50
     Histoire
    0.49
     History
    0.49
     Tobacco
    0.49
     This
    0.48
     Hydro
    0.47
     Monk
    0.47
    Activations Density 0.000%

    No Known Activations