© 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. 116342
    Prev
    Next
    INDEX
    Explanations

    quotation mark followed by pronoun

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

    grant and platform and errors

    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
    edown
    0.46
     UIP
    0.46
     scrollView
    0.44
    e
    0.43
     peso
    0.43
    figuration
    0.41
    現金
    0.41
     simulation
    0.41
    eacute
    0.40
     betek
    0.40
    POSITIVE LOGITS
    今日も
    0.54
     źród
    0.45
     végétaux
    0.44
    状态
    0.43
    오늘은
    0.43
     combustível
    0.43
    ┍
    0.43
     bhavanti
    0.43
     क्वालिटी
    0.43
    avid
    0.43
    Activations Density 0.001%

    No Known Activations