© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 57551
    Prev
    Next
    INDEX
    Explanations

    value creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     اسئله
    0.48
    ソ
    0.46
    內部
    0.43
     lube
    0.42
    [,-
    0.42
     drummer
    0.41
     stylesheet
    0.41
     wither
    0.40
    ಿತು
    0.39
    म्र
    0.39
    POSITIVE LOGITS
     menjalani
    0.46
     Lebih
    0.45
     İ
    0.43
     Ně
    0.43
     officielle
    0.43
    覦
    0.43
     Kolmogorov
    0.42
    Per
    0.42
    ắt
    0.42
    ıl
    0.42
    Activations Density 0.009%

    No Known Activations