© 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. 200009
    Prev
    Next
    INDEX
    Explanations

    whom he

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

    marketing roles and job titles

    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
    Okno
    0.57
    were
    0.56
    ด์
    0.54
    Benzoimidazol
    0.53
    ༔
    0.52
     성능
    0.50
     கடுமையான
    0.50
    ೇಯ
    0.49
     മൃ
    0.49
     방법
    0.49
    POSITIVE LOGITS
     on
    0.50
    <0x9D>
    0.46
     brand
    0.45
    renner
    0.44
    йся
    0.43
    ла
    0.42
     skies
    0.41
    tenberg
    0.41
     mocks
    0.41
     Cancel
    0.41
    Activations Density 0.000%

    No Known Activations