© 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. 38260
    Prev
    Next
    INDEX
    Explanations

    years, political, Coverage

    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
    圴
    0.57
    ല്
    0.55
    нном
    0.53
    мії
    0.52
     erster
    0.52
     investigador
    0.52
     veloce
    0.52
     платье
    0.51
    ᱘
    0.50
    ানীর
    0.49
    POSITIVE LOGITS
    -
    0.56
    afar
    0.52
     (
    0.50
    aim
    0.50
     COVID
    0.49
    isa
    0.49
    oom
    0.46
    \
    0.46
    esh
    0.45
    action
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.