© 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. 68957
    Prev
    Next
    INDEX
    Explanations

    approved close collection speaking sprayed

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

    specifically, particles, prohibited, trees

    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
     insulator
    0.46
     culoare
    0.44
     scary
    0.43
    нил
    0.43
    ્
    0.43
     colorless
    0.43
    чера
    0.42
     $($
    0.42
     dissipative
    0.41
    ருங்க
    0.41
    POSITIVE LOGITS
     längre
    0.51
    驾
    0.50
     ragazzi
    0.49
     eventualmente
    0.48
     vermutlich
    0.47
     mediante
    0.47
     weit
    0.47
     främ
    0.46
    ütz
    0.46
     फिजिक्स
    0.45
    Activations Density 0.001%

    No Known Activations