© 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. 88092
    Prev
    Next
    INDEX
    Explanations

    student award

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

    running embedded systems

    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
    Philippe
    0.50
    琶
    0.50
    ودي
    0.48
    ية
    0.48
    예
    0.48
    asey
    0.47
    IPAL
    0.47
    ﮔ
    0.47
    getMetering
    0.46
    дные
    0.46
    POSITIVE LOGITS
     jail
    0.64
     functional
    0.57
     storage
    0.56
     mice
    0.55
     fibr
    0.55
     enlargement
    0.55
     \'
    0.55
     prison
    0.53
     modulation
    0.53
     sw
    0.52
    Activations Density 0.000%

    No Known Activations