© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 41270
    Prev
    Next
    INDEX
    Explanations

    Power Query and Power BI

    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
    ICON
    0.45
    “
    0.45
    ®,
    0.45
    ell
    0.44
    IDER
    0.44
    Icon
    0.44
    Lean
    0.44
    狍
    0.43
    ©
    0.43
    Ride
    0.42
    POSITIVE LOGITS
     ஏனெனில்
    0.55
     bestimm
    0.49
     endearing
    0.49
     açısından
    0.47
     ஏனெ
    0.46
    жил
    0.45
    hamento
    0.45
     razy
    0.45
     luxuries
    0.45
    یثیت
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.