© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9542
    Prev
    Next
    INDEX
    Explanations

    closing dialog or proximity

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

    close all

    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_40_width_16k_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
    坫
    0.48
    浧
    0.46
    语音
    0.45
    侢
    0.45
    BURG
    0.43
     Rated
    0.43
    內
    0.43
     गर्ल्स
    0.42
    㖩
    0.42
     காலத்தில்
    0.41
    POSITIVE LOGITS
     overflows
    0.39
    antit
    0.39
     floats
    0.39
     floating
    0.39
     absenteeism
    0.38
     enough
    0.37
    Hard
    0.37
    సి
    0.37
     misunder
    0.37
    ml
    0.37
    Activations Density 0.006%

    No Known Activations