© 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. 17362
    Prev
    Next
    INDEX
    Explanations

    [descriptor] followed by [noun]

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

    Magic Keyboard or Swim Vest

    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
     réellement
    0.49
     régler
    0.46
    anjut
    0.46
    imageView
    0.45
     alcanzar
    0.45
    还
    0.45
    ું
    0.45
    ನ್ಸ್
    0.44
    ອີ
    0.44
    Sliders
    0.44
    POSITIVE LOGITS
     DecodingError
    0.46
     項
    0.46
    regation
    0.40
     tzw
    0.40
    ת
    0.39
     sparsity
    0.39
     Baat
    0.38
     vast
    0.37
     Nk
    0.37
     whos
    0.37
    Activations Density 0.000%

    No Known Activations