© 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. 96825
    Prev
    Next
    INDEX
    Explanations

    language or location after separators

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

    financial entries and labels

    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
     természet
    0.48
    hér
    0.45
    拭
    0.44
    耳机
    0.42
    什么的
    0.42
    绒
    0.41
    动漫
    0.41
    炉
    0.41
    ட்ச
    0.41
    ат
    0.41
    POSITIVE LOGITS
     DHA
    0.51
     DSM
    0.48
     Incorporation
    0.48
     Thee
    0.47
     Three
    0.46
     Dukes
    0.46
     DHS
    0.46
    TextColor
    0.45
     instituted
    0.45
     Src
    0.44
    Activations Density 0.001%

    No Known Activations