© 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. 200361
    Prev
    Next
    INDEX
    Explanations

    Did you know that

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

    Did you know that

    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
    MNIST
    0.49
    狂
    0.48
    疆
    0.48
    חו
    0.48
    宗教
    0.47
     mindig
    0.47
     dogma
    0.47
     comte
    0.47
    ﯿ
    0.46
    只好
    0.46
    POSITIVE LOGITS
     |
    0.53
    ::
    0.52
     CG
    0.52
     +
    0.49
     >
    0.48
     our
    0.48
    inae
    0.48
     거의
    0.46
    0
    0.46
    supports
    0.46
    Activations Density 0.002%

    No Known Activations