© 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. 139169
    Prev
    Next
    INDEX
    Explanations

    work less fan their

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

    gears, recovery, nodes, amplify, pressures

    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
     Extraction
    0.54
     oun
    0.52
    utet
    0.52
    arnell
    0.51
    zler
    0.50
    )';
    0.49
     unor
    0.48
     Ane
    0.47
     خواہش
    0.47
    atorul
    0.47
    POSITIVE LOGITS
     meeting
    0.47
    混
    0.44
    控
    0.41
    ществует
    0.40
     gearing
    0.40
     mobilize
    0.40
    团
    0.39
    뵌
    0.39
     gears
    0.39
     פרו
    0.38
    Activations Density 0.001%

    No Known Activations