© 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. 257886
    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
     Marquess
    0.47
     والے
    0.45
     स्क्रिप्ट
    0.45
     صعبه
    0.44
    ällig
    0.43
    剷
    0.43
    terrorism
    0.43
    volution
    0.42
    ropower
    0.42
     جمہوری
    0.42
    POSITIVE LOGITS
    防止
    0.53
    и
    0.52
     источников
    0.47
     BUT
    0.46
    り
    0.46
    不好
    0.45
     principais
    0.45
    ំន
    0.44
     fetches
    0.44
    叮
    0.44
    Activations Density 0.000%

    No Known Activations