© 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. 145640
    Prev
    Next
    INDEX
    Explanations

    future recycling

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

    German and international words

    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
    用地
    0.49
     rebounding
    0.46
    ெ
    0.44
     recovers
    0.44
    ண்
    0.43
    舂
    0.43
    欄
    0.42
    క్ష్
    0.42
    供
    0.41
    মতী
    0.41
    POSITIVE LOGITS
     artikkel
    0.52
     hoved
    0.52
     ří
    0.50
     št
    0.49
    *;
    0.49
     sava
    0.47
    ovka
    0.47
     saker
    0.47
     hlav
    0.46
     raven
    0.46
    Activations Density 0.001%

    No Known Activations