© 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. 116519
    Prev
    Next
    INDEX
    Explanations

    information, prescription, choice, organizational terms

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

    forget everything

    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
    ă
    0.50
    Ş
    0.50
     surfaces
    0.49
     puiss
    0.47
    t
    0.47
     moments
    0.47
     ostr
    0.46
    pero
    0.46
    leş
    0.45
     וע
    0.45
    POSITIVE LOGITS
    動物
    0.48
     Zoological
    0.46
    ಭಾ
    0.46
     ಯೋಜನೆ
    0.46
    臨時
    0.45
     imageHeight
    0.45
     karyawan
    0.44
    亼
    0.44
    მასრულ
    0.44
     సంస్థ
    0.44
    Activations Density 0.001%

    No Known Activations