© 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. 60724
    Prev
    Next
    INDEX
    Explanations

    legal and financial terms

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

    limitations

    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
    醯
    0.52
     crebre
    0.50
     хірур
    0.50
    猞
    0.48
    ]।
    0.48
     batters
    0.47
    देशीर
    0.47
     beagle
    0.46
     thoát
    0.46
    :@"
    0.46
    POSITIVE LOGITS
    love
    0.45
    يت
    0.43
    guided
    0.43
    Rental
    0.43
    pectives
    0.43
    oss
    0.43
    cual
    0.42
    Y
    0.42
    ust
    0.42
     آنلاین
    0.42
    Activations Density 0.000%

    No Known Activations