© 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. 195832
    Prev
    Next
    INDEX
    Explanations

    percent of

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

    legal and financial phrasing

    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
    ר
    0.56
    amnă
    0.50
    więks
    0.50
    üyük
    0.49
    အချိန်
    0.48
    দেবের
    0.47
     enfermo
    0.47
    ב
    0.47
    amay
    0.46
    gespr
    0.46
    POSITIVE LOGITS
    、
    0.61
    製
    0.47
    ،
    0.46
    宜
    0.46
     You
    0.46
     Regardless
    0.45
    張
    0.45
     Perhaps
    0.45
    浸
    0.44
    團
    0.43
    Activations Density 0.000%

    No Known Activations