© 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. 156855
    Prev
    Next
    INDEX
    Explanations

    arranged almost

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

    intensifiers and qualifiers

    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
     dịp
    0.52
     сведения
    0.48
    लील
    0.46
    न
    0.45
    デート
    0.45
    П
    0.45
    ルト
    0.44
    Р
    0.44
     Nhật
    0.44
    MovieDetails
    0.44
    POSITIVE LOGITS
    ed
    0.48
    -(
    0.48
     já
    0.47
     -
    0.47
     بأ
    0.47
    していますが
    0.46
     করিয়ে
    0.46
     ""
    0.45
    allelujah
    0.44
     (
    0.44
    Activations Density 0.000%

    No Known Activations