© 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. 234732
    Prev
    Next
    INDEX
    Explanations

    respectively, collarbone, advanced training

    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
     בא
    0.53
     പരിശ
    0.49
     প্রোগ্র
    0.47
     ک
    0.47
     Strickland
    0.46
     ဖြစ်
    0.45
     කරන්න
    0.45
     পারে
    0.44
     博文
    0.44
     actomyosin
    0.44
    POSITIVE LOGITS
    璉
    0.51
     whereby
    0.50
    ेल
    0.45
    ern
    0.45
     cuyas
    0.44
    ≙
    0.44
    対
    0.43
    دام
    0.42
     esque
    0.42
    தேசம்
    0.42
    Activations Density 0.000%

    No Known Activations