© 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. 74015
    Prev
    Next
    INDEX
    Explanations

    severe allergic, hardest work

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

    someone else, like toothpaste

    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
    普通的
    0.44
    Bits
    0.42
    普通
    0.42
    方面
    0.41
    F
    0.41
    R
    0.40
    C
    0.40
    废
    0.38
    选举
    0.38
    BITS
    0.38
    POSITIVE LOGITS
     sulfates
    0.50
    🤛
    0.49
    𐰚
    0.49
     depositphotos
    0.48
    ഹൃ
    0.48
     belir
    0.48
    ناك
    0.47
     (\<
    0.47
    protein
    0.47
    prestations
    0.47
    Activations Density 0.001%

    No Known Activations