© 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. 259508
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Technologien
    0.57
     Sereth
    0.56
    𝗌
    0.56
    鏻
    0.52
    镰
    0.52
    焓
    0.51
    湿度
    0.51
     전통
    0.51
    델
    0.50
    枥
    0.50
    POSITIVE LOGITS
    care
    0.54
    em
    0.51
     every
    0.51
    ed
    0.51
     anything
    0.51
    est
    0.49
    any
    0.47
    one
    0.46
     but
    0.46
     mercy
    0.46
    Activations Density 0.000%

    No Known Activations