© 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. 149244
    Prev
    Next
    INDEX
    Explanations

    speech respiration articulation

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

    section at the end

    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
     Hispanics
    0.49
    س
    0.48
    న
    0.46
     transportar
    0.44
    ूला
    0.43
    وم
    0.43
    फिया
    0.42
     начина
    0.42
    AsUp
    0.42
     dekor
    0.41
    POSITIVE LOGITS
    élève
    0.49
    질
    0.47
     respiratoires
    0.45
     énorm
    0.45
     기준으로
    0.45
    $$\
    0.45
     constellation
    0.44
     activité
    0.44
     කා
    0.43
    baw
    0.43
    Activations Density 0.000%

    No Known Activations