© 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. 163850
    Prev
    Next
    INDEX
    Explanations

    letter matrix system

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

    self-improvement or attraction

    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
    \
    0.56
     covariance
    0.48
     hét
    0.47
    (
    0.47
    。
    0.46
    ետ
    0.44
    刑
    0.44
    河流
    0.43
    離開
    0.43
    Cov
    0.42
    POSITIVE LOGITS
     Stickers
    0.56
    olot
    0.53
    ேட்
    0.51
    ोत्सव
    0.51
     מצ
    0.50
    ie
    0.50
     Dons
    0.49
    ായി
    0.47
    pett
    0.47
    Payload
    0.47
    Activations Density 0.000%

    No Known Activations