© 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. 94977
    Prev
    Next
    INDEX
    Explanations

    copyright notices and years

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

    Recent years and updates

    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
     I
    0.46
    ##
    0.45
    od
    0.42
     NN
    0.42
     ошиб
    0.42
    lation
    0.42
    of
    0.42
    m
    0.41
     MN
    0.41
    yam
    0.41
    POSITIVE LOGITS
    ادة
    0.45
     ważne
    0.44
    ژ
    0.44
     सीजन
    0.44
     njeg
    0.42
    ری
    0.40
    ائز
    0.40
     شاب
    0.40
     IntPtr
    0.40
     Ответ
    0.40
    Activations Density 0.011%

    No Known Activations