© 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. 231827
    Prev
    Next
    INDEX
    Explanations

    verification tests, Muslim Brotherhood

    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
    a
    0.66
    ه
    0.57
    p
    0.53
    dynamic
    0.52
    drink
    0.49
    player
    0.47
    ebut
    0.46
    '%
    0.45
    rag
    0.44
    exception
    0.44
    POSITIVE LOGITS
     civilized
    0.50
     моём
    0.50
    ደት
    0.48
     своём
    0.47
    偻
    0.46
     हाथों
    0.45
     hob
    0.45
     стане
    0.45
     formalized
    0.45
     CORPOR
    0.45
    Activations Density 0.001%

    No Known Activations