© 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. 159608
    Prev
    Next
    INDEX
    Explanations

    latest exam video Microsoft Certified

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

    Client initialization or definition

    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
     Boden
    0.55
    ла
    0.51
     పరిష్
    0.49
     Fälle
    0.48
     மகள்
    0.46
    f
    0.46
     случаев
    0.43
    boden
    0.43
    雹
    0.43
     председа
    0.43
    POSITIVE LOGITS
     ratio
    0.52
     kan
    0.49
     manufacturing
    0.48
     intake
    0.47
     printing
    0.47
     litre
    0.46
     mott
    0.46
     amount
    0.46
     kind
    0.46
     deliver
    0.45
    Activations Density 0.001%

    No Known Activations