© 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. 87427
    Prev
    Next
    INDEX
    Explanations

    finding outcomes and next steps

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

    controls access

    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
    ᓵ
    0.54
    ইউনি
    0.52
    UN
    0.51
    頨
    0.50
    Practice
    0.48
    indazol
    0.48
    唑
    0.48
    ثال
    0.47
    ീല
    0.47
    苄
    0.47
    POSITIVE LOGITS
     cr
    0.61
     Dec
    0.52
    st
    0.52
     calm
    0.50
     seams
    0.50
     giants
    0.50
     deciding
    0.49
     aisles
    0.48
     lovers
    0.48
     hiking
    0.47
    Activations Density 0.000%

    No Known Activations