© 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. 203661
    Prev
    Next
    INDEX
    Explanations

    declarations of facts or statements

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

    explaining what something is

    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
    甑
    0.52
    🤕
    0.48
    πος
    0.47
     വേദന
    0.46
    enderita
    0.46
    securityMarks
    0.46
     Разби
    0.45
    션
    0.45
    Բ
    0.45
     ადამიან
    0.45
    POSITIVE LOGITS
    will
    0.49
     ifs
    0.48
     AS
    0.48
     [
    0.47
     Blu
    0.46
    u
    0.46
    c
    0.45
     will
    0.44
     ISS
    0.44
    cf
    0.43
    Activations Density 0.000%

    No Known Activations