© 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. 53250
    Prev
    Next
    INDEX
    Explanations

    common word pairings

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

    pixel blooms and space

    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
    有料
    0.55
    ܝܢ
    0.45
     stats
    0.40
    GING
    0.40
    벌
    0.40
    けど
    0.39
    ंत्रित
    0.39
    เอ
    0.39
    pointing
    0.39
    ਧ
    0.39
    POSITIVE LOGITS
     Intens
    0.46
     glaz
    0.44
     Aire
    0.44
     Imagin
    0.43
     yaşam
    0.42
     garder
    0.41
     Launches
    0.41
     красо
    0.41
     Fonts
    0.41
     ويل
    0.41
    Activations Density 0.000%

    No Known Activations