© 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. 87448
    Prev
    Next
    INDEX
    Explanations

    time management, Bishop Ready High School, fully integrated, Deliver

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

    sexual content and code repositories

    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
     होके
    0.51
     UK
    0.49
     Uses
    0.47
     tuh
    0.45
    ȩ
    0.45
    また
    0.44
     Trans
    0.43
     해
    0.43
     উপমহাদেশ
    0.43
     inject
    0.43
    POSITIVE LOGITS
     didReceive
    0.49
    FieldNumber
    0.48
    Gir
    0.46
    APs
    0.44
    %$$
    0.43
    DBObject
    0.43
    girl
    0.43
    GameObject
    0.43
    BinaryOperation
    0.42
    Printer
    0.42
    Activations Density 0.001%

    No Known Activations