© 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. 31726
    Prev
    Next
    INDEX
    Explanations

    the other

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

    rollout or compromise

    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
    planet
    0.50
    i
    0.49
    ٧
    0.46
    OLE
    0.44
    seb
    0.44
    @@
    0.44
    ʎ
    0.43
    啤
    0.43
     गये
    0.42
    农民
    0.42
    POSITIVE LOGITS
     adequately
    0.47
     automobiles
    0.46
     মুহ
    0.45
     everything
    0.45
    ষ্ঠান
    0.45
     autonomous
    0.45
     your
    0.44
     Flows
    0.44
     confidently
    0.44
     whol
    0.44
    Activations Density 0.000%

    No Known Activations