© 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. 260632
    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
    咆
    0.44
    damaged
    0.43
    صر
    0.43
     lesz
    0.42
     erro
    0.41
    طف
    0.40
    之後
    0.40
    ły
    0.40
    虔
    0.39
    ফাজ
    0.39
    POSITIVE LOGITS
     మరియు
    0.55
     toJson
    0.47
     તેમજ
    0.44
    <0x1E>
    0.43
     এবং
    0.43
     અને
    0.43
    妈
    0.43
    மிருந்து
    0.43
     Spread
    0.42
    ிட
    0.42
    Activations Density 0.000%

    No Known Activations