© 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. 242923
    Prev
    Next
    INDEX
    Explanations

    education, require, defer, depicts

    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
    场所
    0.48
    iding
    0.48
     consacré
    0.48
    箇
    0.45
    SO
    0.44
     ይህ
    0.44
    IDING
    0.44
    TO
    0.44
    таў
    0.43
     doskona
    0.43
    POSITIVE LOGITS
    argeon
    0.50
     CNBC
    0.48
     MND
    0.45
     UVB
    0.45
     illegitimate
    0.42
     juríd
    0.42
     CBP
    0.42
    userDetail
    0.41
    ).__
    0.41
    wirkung
    0.41
    Activations Density 0.000%

    No Known Activations