© 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. 172733
    Prev
    Next
    INDEX
    Explanations

    "Rolls" and "state"

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

    sentence correction advice

    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
     ৪৯
    0.50
     ಒ
    0.45
    atation
    0.44
    并购
    0.44
    টিত
    0.43
    对应
    0.43
     مشرف
    0.42
     밤
    0.42
    imod
    0.41
     বর্ণিত
    0.41
    POSITIVE LOGITS
    Ế
    0.46
     Carg
    0.41
    '
    0.41
     relying
    0.41
     información
    0.40
     horm
    0.39
     chim
    0.39
     Nhi
    0.39
    Гор
    0.39
     Kih
    0.38
    Activations Density 0.001%

    No Known Activations