© 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. 161121
    Prev
    Next
    INDEX
    Explanations

    stages, reading, Mark, test, reactors

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

    rounded number

    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
    氩
    0.59
    速率
    0.51
     ሌ
    0.50
     ആക്രമ
    0.50
     Bör
    0.50
     午
    0.47
    ريبة
    0.47
    Ņ
    0.47
    UIAlert
    0.47
     把
    0.46
    POSITIVE LOGITS
     to
    0.55
     of
    0.54
     stages
    0.49
     COMPLET
    0.48
    p
    0.46
    том
    0.46
    рын
    0.46
    ul
    0.44
    𝟭
    0.44
     OF
    0.44
    Activations Density 0.000%

    No Known Activations