© 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. 252697
    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
    ?
    0.53
     Dirac
    0.45
     Selected
    0.43
    ியின்
    0.43
     uniformed
    0.43
     Budapest
    0.43
     gyárt
    0.43
    瀞
    0.42
    uje
    0.41
    lerinden
    0.41
    POSITIVE LOGITS
    affaires
    0.59
    ătate
    0.49
     تاک
    0.49
    дин
    0.48
    мос
    0.47
    دید
    0.47
    ائ
    0.47
    اف
    0.47
     própri
    0.46
    假的
    0.46
    Activations Density 0.002%

    No Known Activations