© 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. 66812
    Prev
    Next
    INDEX
    Explanations

    legal terms

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

    technical terms and common words

    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
    ната
    0.43
    뿍
    0.43
    很
    0.43
    阳
    0.42
    它们的
    0.41
    ，
    0.41
    </strong>
    0.41
     multin
    0.39
    <strong>
    0.39
    unakan
    0.39
    POSITIVE LOGITS
    िनियम
    0.53
    ographie
    0.46
    uesday
    0.46
     ഉള്‍
    0.45
    pèce
    0.43
    Scanning
    0.42
     площадь
    0.42
    emporary
    0.42
    ebel
    0.42
     площади
    0.42
    Activations Density 0.000%

    No Known Activations