© 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. 85062
    Prev
    Next
    INDEX
    Explanations

    survival and actions

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

    UI Panel, Document, Off

    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
    ·
    0.49
    RING
    0.48
    Ā
    0.46
    动物
    0.45
    lains
    0.45
    ubuntu
    0.45
     Amiri
    0.44
     Asante
    0.44
    <em>
    0.43
    笼
    0.43
    POSITIVE LOGITS
     intersects
    0.59
     giữa
    0.56
     increases
    0.53
     quedan
    0.50
     queda
    0.47
     correctamente
    0.47
     tăng
    0.46
     décès
    0.46
     comunic
    0.45
     aumentar
    0.45
    Activations Density 0.000%

    No Known Activations