© 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. 157432
    Prev
    Next
    INDEX
    Explanations

    good nature

    np_acts-logits-general · gemini-2.5-flash-lite

    pointer files, choose to, NVM

    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
    RIM
    0.46
    ξει
    0.46
    في
    0.45
    ATUS
    0.44
    鏗
    0.44
     Bioinformatics
    0.43
    aS
    0.43
    딥
    0.43
     ಮಾತ
    0.42
    AX
    0.41
    POSITIVE LOGITS
    中所
    0.51
    []>
    0.50
     아니고
    0.48
     несо
    0.47
     ชื่อ
    0.46
    notlocked
    0.45
     স্বীকার
    0.44
     جر
    0.44
     новое
    0.44
     воору
    0.44
    Activations Density 0.000%

    No Known Activations