© 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. 135091
    Prev
    Next
    INDEX
    Explanations

    business, services, order, skills, lights, European

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

    population peaks

    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
    。</
    0.58
    。
    0.50
    。【
    0.50
    。[
    0.48
    。...
    0.47
    ។
    0.47
     happenings
    0.46
    ્ર
    0.45
    rasında
    0.45
    }.
    0.45
    POSITIVE LOGITS
    ROOM
    0.52
    nicht
    0.51
     Room
    0.44
    াহিনী
    0.44
     Gleich
    0.43
    Nicht
    0.42
    ರ್ಧ
    0.42
    ટક
    0.42
     nee
    0.42
    Room
    0.41
    Activations Density 0.000%

    No Known Activations