© 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. 23894
    Prev
    Next
    INDEX
    Explanations

    p-values and inequalities

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

    linear fit

    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
    스
    0.48
    자
    0.47
     دقیق
    0.43
    exact
    0.43
    Exact
    0.41
    precise
    0.41
    exactly
    0.40
    شی
    0.39
     ugl
    0.39
    랍
    0.39
    POSITIVE LOGITS
    umos
    0.48
    ické
    0.45
    ించిన
    0.44
     લ
    0.43
     Lloyds
    0.43
     కా
    0.42
    étel
    0.42
     Лондон
    0.42
    రించ
    0.41
     $[-
    0.41
    Activations Density 0.000%

    No Known Activations