© 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. 240613
    Prev
    Next
    INDEX
    Explanations

    Organ performer

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    精彩
    0.45
    细菌
    0.45
    \
    0.44
    )。
    0.43
    使える
    0.43
    )，
    0.42
    💟
    0.42
     версию
    0.41
    潍
    0.41
    ட்ட
    0.41
    POSITIVE LOGITS
     سسٹم
    0.55
     concomit
    0.48
     entirety
    0.47
     सांगितलं
    0.47
    external
    0.46
     surpl
    0.46
    correction
    0.46
     princ
    0.46
     externa
    0.46
     correction
    0.45
    Activations Density 0.003%

    No Known Activations