© 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. 70657
    Prev
    Next
    INDEX
    Explanations

    one of the

    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
    4
    0.17
    6
    0.17
     {
    0.17
    0
    0.17
    2
    0.16
     I
    0.16
    M
    0.16
    5
    0.16
    3
    0.16
    s
    0.15
    POSITIVE LOGITS
     countenance
    0.14
     viciss
    0.13
     pept
    0.13
     protop
    0.13
    лага
    0.13
     exalt
    0.13
    פה
    0.13
    覇
    0.13
    ској
    0.12
     condensate
    0.12
    Activations Density 0.000%

    No Known Activations