© 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. 47492
    Prev
    Next
    INDEX
    Explanations

    even yoga

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

    function hide or describe state

    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
    ak
    0.49
     fu
    0.48
     Eng
    0.46
     Tick
    0.45
     bez
    0.44
     Tarif
    0.44
     hulk
    0.44
    '};
    0.44
    eluk
    0.44
     Eden
    0.44
    POSITIVE LOGITS
    ISTANCE
    0.56
    鱻
    0.50
    IGHT
    0.50
    вла
    0.50
    LLA
    0.48
    Ꮬ
    0.48
    Coastal
    0.48
     आरएफ
    0.47
     அவசியம்
    0.47
    闓
    0.47
    Activations Density 0.000%

    No Known Activations