© 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. 57844
    Prev
    Next
    INDEX
    Explanations

    .for Androidapply toof Liquid) country

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

    contact information or durations

    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
     návr
    0.46
    ريك
    0.44
    臻
    0.42
    ᾖ
    0.42
    ริ
    0.42
    новниш
    0.42
     aportan
    0.42
    Testables
    0.41
    Exceptionally
    0.41
     postcss
    0.41
    POSITIVE LOGITS
     기름
    0.47
     כאשר
    0.44
     ನಿಜ
    0.43
     황
    0.42
    utzer
    0.42
     respectiv
    0.42
    mär
    0.42
     które
    0.41
     Capacitor
    0.41
     ย
    0.41
    Activations Density 0.000%

    No Known Activations