© 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. 241904
    Prev
    Next
    INDEX
    Explanations

    service providers

    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
     Agricultura
    0.50
    钏
    0.50
     femenino
    0.50
     motocicleta
    0.50
     Teknologi
    0.49
    ιβ
    0.49
    쫀
    0.49
    纤维
    0.48
     Incluso
    0.47
    伱
    0.47
    POSITIVE LOGITS
     Saturday
    0.53
    basically
    0.51
    Saturday
    0.50
    ish
    0.48
     impug
    0.48
     uneven
    0.47
     inhomogeneity
    0.47
    concrete
    0.46
     wider
    0.46
    akai
    0.46
    Activations Density 0.000%

    No Known Activations