© 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. 117701
    Prev
    Next
    INDEX
    Explanations

    hierarchy and constructs

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

    can help

    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
    內
    0.51
     распро
    0.48
     blacksmith
    0.48
    Dried
    0.47
     ပဲ
    0.47
     redondo
    0.47
     لري
    0.46
     ትንሽ
    0.46
     ক্ষুদ্র
    0.46
     风
    0.45
    POSITIVE LOGITS
     i
    0.50
    ند
    0.50
    和你
    0.44
     attacc
    0.44
    >
    0.44
    立
    0.44
     सुरु
    0.43
     AppModule
    0.43
    🇴
    0.42
    許可
    0.42
    Activations Density 0.000%

    No Known Activations