© 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. 57567
    Prev
    Next
    INDEX
    Explanations

    earnings from the

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

    order of things, from lowest to highest

    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
    轮回
    0.46
    트에
    0.46
    olata
    0.45
     влияние
    0.45
    见
    0.45
     вариантов
    0.44
    랍니다
    0.44
    必备
    0.44
     말미암
    0.43
    ዖ
    0.43
    POSITIVE LOGITS
     recomiendo
    0.46
     combines
    0.45
     primero
    0.45
     ignores
    0.45
     ester
    0.44
     melindungi
    0.44
     adapts
    0.44
     blends
    0.43
     ofrece
    0.43
     synerg
    0.42
    Activations Density 0.000%

    No Known Activations