© 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. 237328
    Prev
    Next
    INDEX
    Explanations

    little princess

    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
    Institut
    0.56
    ய
    0.56
    Tet
    0.54
    IM
    0.52
    Ela
    0.51
    ५
    0.50
    HM
    0.49
    की
    0.49
    Ç
    0.49
    Das
    0.49
    POSITIVE LOGITS
    acks
    0.55
    icks
    0.47
     不是
    0.45
     oaks
    0.44
     renewables
    0.43
     Talend
    0.42
    ść
    0.42
     followers
    0.42
    onan
    0.42
     lows
    0.41
    Activations Density 0.001%

    No Known Activations