© 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. 194993
    Prev
    Next
    INDEX
    Explanations

    print your own text

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

    facility maintenance

    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
    h
    0.56
    스러운
    0.50
    imated
    0.48
     voit
    0.47
    x
    0.47
    ometric
    0.47
    umpul
    0.47
     sérieux
    0.46
     µ
    0.46
     wt
    0.46
    POSITIVE LOGITS
    和社会
    0.49
    مة
    0.49
    Пи
    0.49
    旄
    0.48
    茆
    0.46
    私
    0.45
    כל
    0.44
    Cómo
    0.44
    राबरी
    0.44
    巴
    0.44
    Activations Density 0.000%

    No Known Activations