© 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. 188827
    Prev
    Next
    INDEX
    Explanations

    Of all, for industrial, animated After

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

    consider if traditional gender Airline communication

    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
    u
    0.49
     fractional
    0.47
     deducted
    0.45
    itation
    0.43
     EOS
    0.43
     D
    0.42
    laub
    0.42
     deduced
    0.41
    +"/
    0.41
    শিয়া
    0.40
    POSITIVE LOGITS
     नु
    0.50
     oczywiście
    0.50
     ακόμα
    0.48
    બસ
    0.47
    アニメ
    0.46
     évidemment
    0.46
    utenants
    0.46
    胃
    0.45
    ⵥ
    0.45
     ઉત્
    0.45
    Activations Density 0.001%

    No Known Activations