© 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. 166453
    Prev
    Next
    INDEX
    Explanations

    photo of places

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

    breakdown, covering

    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
    러스
    0.45
    лар
    0.45
    櫂
    0.45
    Rak
    0.44
    新
    0.44
    пель
    0.43
    ти
    0.43
    壓
    0.43
    꾹
    0.43
    ज़ार
    0.42
    POSITIVE LOGITS
     epidemiological
    0.61
     Utilizing
    0.52
     Epidemi
    0.51
     adjoining
    0.51
     Andromeda
    0.51
     Utilize
    0.50
     Hamming
    0.50
     circumstellar
    0.49
     Detailed
    0.48
     Nxf
    0.48
    Activations Density 0.000%

    No Known Activations