© 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. 33624
    Prev
    Next
    INDEX
    Explanations

    named professions

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

    providing explanations and breakdowns

    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
    血管
    0.53
     atthakath
    0.52
    爱好
    0.52
     பாதிக்கிறது
    0.52
     gahet
    0.51
     ತಯಾರ
    0.51
    塗り
    0.50
    癌
    0.50
     giocando
    0.49
    preliquidacion
    0.49
    POSITIVE LOGITS
    <b>
    0.51
    in
    0.47
     Harry
    0.46
     Harrison
    0.46
     Horace
    0.44
     Jin
    0.44
     Hor
    0.44
     sequential
    0.44
    Hor
    0.42
    л
    0.42
    Activations Density 0.000%

    No Known Activations