© 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. 258137
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     späteren
    0.48
     nhạc
    0.47
    üten
    0.46
     Tutti
    0.45
    ើ
    0.45
    رشف
    0.44
     escult
    0.44
    不会
    0.43
    рики
    0.42
     остаются
    0.42
    POSITIVE LOGITS
     באמצעות
    0.60
    ATED
    0.55
     স্থান
    0.51
    ATIVE
    0.50
    FormProvider
    0.50
    Θ
    0.50
    WD
    0.49
    AND
    0.49
     เกี่ยว
    0.49
    Φ
    0.49
    Activations Density 0.001%

    No Known Activations