© 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. 172756
    Prev
    Next
    INDEX
    Explanations

    non-english characters

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

    function calls or list items

    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
    i
    0.50
    tel
    0.49
     cancel
    0.47
    tent
    0.45
     separ
    0.44
    Crossing
    0.44
    img
    0.43
    temperatur
    0.43
     Weltkrieg
    0.42
     spezial
    0.42
    POSITIVE LOGITS
    酯
    0.50
    ด
    0.45
    rimiento
    0.44
    𝘖
    0.44
    َس
    0.43
     unleashed
    0.42
    勂
    0.42
     enshrined
    0.42
    ιση
    0.41
     વિદ્ય
    0.41
    Activations Density 0.000%

    No Known Activations