© 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. 249313
    Prev
    Next
    INDEX
    Explanations

    and, or, but

    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
     Pay
    0.51
     Poor
    0.50
     Coke
    0.50
     R
    0.47
    DON
    0.47
     Time
    0.46
    will
    0.46
    pragma
    0.46
     listens
    0.46
     RIP
    0.46
    POSITIVE LOGITS
     успо
    0.55
     ή
    0.51
    संधान
    0.50
     এতো
    0.50
    新疆
    0.49
     महिला
    0.49
    或其他
    0.48
     بهبود
    0.45
     ಹೆಚ್ಚ
    0.45
     devenue
    0.45
    Activations Density 0.000%

    No Known Activations