© 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. 133831
    Prev
    Next
    INDEX
    Explanations

    spiritual concepts and denial

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

    options are not lottery

    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
     הצ
    0.54
    C
    0.52
    </td>
    0.49
    ,
    0.48
    INGS
    0.46
     הע
    0.45
    ል
    0.45
    ล
    0.45
    ↵↵
    0.44
    ন
    0.44
    POSITIVE LOGITS
    فرق
    0.48
     witchcraft
    0.45
     pretende
    0.44
     mesurer
    0.44
     rétréci
    0.43
    слары
    0.43
    बीयत
    0.43
     paranormal
    0.42
    discipl
    0.42
    是對
    0.42
    Activations Density 0.000%

    No Known Activations