© 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. 228817
    Prev
    Next
    INDEX
    Explanations

    Teddy Bear, portal, essay, unit

    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
    t
    0.66
     cooks
    0.54
    line
    0.51
    size
    0.50
    wide
    0.50
    tornado
    0.50
    mega
    0.50
    new
    0.50
    tede
    0.50
    谭
    0.50
    POSITIVE LOGITS
    良く
    0.51
    丁寧
    0.50
    ۔
    0.49
     "-//
    0.45
     цього
    0.44
    โก
    0.43
     জানায়
    0.42
    致します
    0.42
    雖然
    0.42
    อย่าง
    0.42
    Activations Density 0.000%

    No Known Activations