© 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. 254760
    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
     Руси
    0.48
    ü
    0.46
    ending
    0.46
    nada
    0.45
    ed
    0.44
    edes
    0.44
    osa
    0.44
    é
    0.43
     त्यानंतर
    0.43
    ème
    0.43
    POSITIVE LOGITS
     koska
    0.46
    INGER
    0.46
    DWORD
    0.44
    每日
    0.42
     uyg
    0.42
    LIK
    0.42
     codzien
    0.41
     malleable
    0.41
     parametr
    0.40
     implication
    0.40
    Activations Density 0.000%

    No Known Activations