© 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. 98010
    Prev
    Next
    INDEX
    Explanations

    whilst on, afford it, your family

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

    arithmetic calculation presentation

    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
    蜮
    0.52
     collegamento
    0.51
     цьому
    0.49
    десят
    0.47
    лось
    0.46
     понрави
    0.46
     زیرمه
    0.45
     lediglich
    0.44
     этом
    0.44
     مجموعة
    0.44
    POSITIVE LOGITS
    나
    0.49
     approach
    0.45
     METHOD
    0.45
    mph
    0.44
    Endpoint
    0.43
    도
    0.42
    resa
    0.42
     DREAM
    0.42
     APPROACH
    0.42
    ITION
    0.41
    Activations Density 0.001%

    No Known Activations