© 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. 197253
    Prev
    Next
    INDEX
    Explanations

    historical entities and objects

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

    resource usage

    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
    subdir
    0.48
    tem
    0.48
    텁
    0.47
    miy
    0.47
    푞
    0.46
    𝓃
    0.46
    subdirectory
    0.46
     रवा
    0.46
    tn
    0.46
    किट
    0.46
    POSITIVE LOGITS
     You
    0.50
     ремонт
    0.48
    <u>
    0.46
     Ferry
    0.46
    Donate
    0.46
    You
    0.45
    Tomorrow
    0.44
     Symphony
    0.44
     More
    0.43
     Tourist
    0.43
    Activations Density 0.000%

    No Known Activations