© 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. 104311
    Prev
    Next
    INDEX
    Explanations

    also try, also want, also become

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

    Latin names

    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
    T
    0.47
    :
    0.45
     Edge
    0.45
     Tolerance
    0.45
     (
    0.44
    7
    0.44
     Emp
    0.43
    C
    0.42
     Experimental
    0.42
     Gator
    0.42
    POSITIVE LOGITS
     அதிசயங்கள்
    0.57
     効果
    0.54
    ವಾರು
    0.49
     நீண்ட
    0.49
    InsertInt
    0.49
    アイコン
    0.49
     പര
    0.48
     ಕಬ್ಬಿಣ
    0.48
     ধারাবাহিক
    0.48
    <unused70>
    0.48
    Activations Density 0.000%

    No Known Activations