© 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. 254779
    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
     ouvrir
    0.49
    ین
    0.49
     problèmes
    0.47
    উন্ড
    0.47
     nayo
    0.47
     m
    0.46
    isième
    0.46
     kommer
    0.45
    블
    0.45
    istä
    0.45
    POSITIVE LOGITS
     }),
    0.46
    FindAction
    0.45
    助
    0.45
    ]।
    0.44
    Corp
    0.43
    ।
    0.43
     કરે
    0.42
    こそ
    0.41
    edt
    0.41
    <0x19>
    0.40
    Activations Density 0.000%

    No Known Activations