© 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. 195032
    Prev
    Next
    INDEX
    Explanations

    professional or academic programs

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

    Calvary Chapel

    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
    ailand
    0.46
    েশ
    0.43
     कथित
    0.42
    atsion
    0.42
    ়
    0.41
     børn
    0.40
    գ
    0.39
    DataProvider
    0.39
    骶
    0.39
    ve
    0.38
    POSITIVE LOGITS
    COL
    0.49
     Pione
    0.49
     меч
    0.49
    TRANSFER
    0.48
     TRANSFER
    0.47
    0.47
     PEN
    0.45
     SPACE
    0.45
    ASSOC
    0.45
     FAM
    0.44
    Activations Density 0.001%

    No Known Activations