© 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. 222338
    Prev
    Next
    INDEX
    Explanations

    should be, signal sounds, item in

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

    verge of / budget option

    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
    ྥ
    0.51
     Begin
    0.48
     selectInput
    0.46
     BEGIN
    0.45
     CAROLINA
    0.44
     MEMBERS
    0.44
    と一緒に
    0.43
    ্টর
    0.43
    젹
    0.43
     Expression
    0.42
    POSITIVE LOGITS
     مهمه
    0.51
     gneiss
    0.49
    am
    0.49
    रेख
    0.49
     सिद्धार्थ
    0.46
     meditative
    0.46
     ثالث
    0.46
     ث
    0.45
     pericard
    0.45
    érico
    0.45
    Activations Density 0.000%

    No Known Activations