© 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. 75284
    Prev
    Next
    INDEX
    Explanations

    size photo or gallery

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

    voice speaking or sounding

    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
     Ayl
    0.50
     Scholars
    0.44
    áus
    0.40
     Edo
    0.40
    ddd
    0.40
    熠
    0.39
     উদার
    0.39
    ἢ
    0.39
    ுடைய
    0.39
     Strengthen
    0.38
    POSITIVE LOGITS
     royaume
    0.46
     reductions
    0.46
     kinetics
    0.45
    ྭ
    0.45
     mortgages
    0.44
    INCLUDING
    0.44
     devaluation
    0.44
     habitat
    0.44
    opers
    0.44
     fabri
    0.44
    Activations Density 0.001%

    No Known Activations