© 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. 120408
    Prev
    Next
    INDEX
    Explanations

    listing topics and details

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

    consequences for striving

    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
    ן
    0.61
    ا
    0.51
    ynge
    0.49
     தன்
    0.47
     fortiter
    0.47
    ו
    0.45
     efectu
    0.45
    ペン
    0.45
    нак
    0.45
    Хар
    0.45
    POSITIVE LOGITS
     flooring
    0.47
    ุน
    0.46
    <0xAF>
    0.45
    theon
    0.45
     numar
    0.45
     sanitation
    0.44
    DEP
    0.44
     civilized
    0.43
     barracks
    0.42
    сів
    0.42
    Activations Density 0.000%

    No Known Activations