© 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. 149322
    Prev
    Next
    INDEX
    Explanations

    writing about poetry and understanding

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

    database, plan, competition, framework

    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
    ="
    0.55
    usi
    0.53
    gca
    0.53
    ango
    0.52
    usa
    0.52
    acha
    0.51
    yam
    0.50
    बाय
    0.48
     teorías
    0.48
     lesiones
    0.47
    POSITIVE LOGITS
    郗
    0.51
    ﺭ
    0.48
    𝐕
    0.47
    ान्
    0.46
    ુ
    0.46
     microbe
    0.45
     understand
    0.45
     Kernel
    0.45
     bathtub
    0.44
     sekt
    0.44
    Activations Density 0.000%

    No Known Activations