© 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. 98717
    Prev
    Next
    INDEX
    Explanations

    transaction verbs

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

    foreign words and specific topics

    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
     menacing
    0.48
    聪
    0.42
    adir
    0.42
    ிலோ
    0.41
    ູບ
    0.41
    بیه
    0.40
     journalistic
    0.40
     지정
    0.39
    鉾
    0.39
     threatening
    0.38
    POSITIVE LOGITS
    運輸
    0.44
     অল্প
    0.44
     transported
    0.42
    內的
    0.42
    ために
    0.42
    <unused374>
    0.42
     jestem
    0.41
     عمليات
    0.41
    옮
    0.41
     resumed
    0.41
    Activations Density 0.000%

    No Known Activations