© 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. 242160
    Prev
    Next
    INDEX
    Explanations

    rapping, rapper, Chicago

    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
    ீரி
    0.58
    ிற்ப
    0.54
    鳧
    0.52
    摭
    0.52
    鋆
    0.52
    İZ
    0.50
    ዝና
    0.49
    嫄
    0.46
    нера
    0.46
    訕
    0.46
    POSITIVE LOGITS
    ja
    0.49
    oma
    0.48
    ach
    0.47
     rapping
    0.46
     rapper
    0.46
    ↵↵
    0.43
    ha
    0.43
     oat
    0.43
    oa
    0.42
     Chicago
    0.42
    Activations Density 0.000%

    No Known Activations