© 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. 260602
    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
    矮
    0.49
    マイ
    0.45
    df
    0.45
    ダイ
    0.44
    挛
    0.44
     hidrául
    0.44
    दिया
    0.43
    ニコ
    0.42
    ियारों
    0.42
    बो
    0.41
    POSITIVE LOGITS
    arrival
    0.47
    arrivals
    0.47
     cheg
    0.45
    agar
    0.43
     rapat
    0.42
     chemot
    0.42
    促進
    0.42
    爺
    0.42
    sunline
    0.41
    achella
    0.41
    Activations Density 0.000%

    No Known Activations