© 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. 168989
    Prev
    Next
    INDEX
    Explanations

    software program, detected that, irritating effect

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

    exploited bugs, monitor browsing

    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
     sympathize
    0.49
     eloquently
    0.46
    \"",
    0.44
    ჩ
    0.43
     guérir
    0.42
     basses
    0.41
     véritables
    0.41
     unsurprisingly
    0.40
     aires
    0.40
     sympathies
    0.39
    POSITIVE LOGITS
     של
    0.56
     Nutrition
    0.54
    acion
    0.50
    蠵
    0.49
     Gosudarstvennyj
    0.49
     अनन्या
    0.47
    oxins
    0.46
    馇
    0.46
    馗
    0.46
    Nutrition
    0.46
    Activations Density 0.001%

    No Known Activations