© 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. 127090
    Prev
    Next
    INDEX
    Explanations

    exclude sub-OU

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

    lines after triangle

    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
    <0xE2>
    0.45
    &
    0.40
     &
    0.37
    *
    0.37
    还有
    0.36
    還有
    0.36
    ================
    0.35
    amins
    0.35
    Assets
    0.34
     किस्मत
    0.34
    POSITIVE LOGITS
     정사각형
    0.44
     алгорит
    0.42
     perspici
    0.42
     gruppi
    0.42
     pédicule
    0.41
    筅
    0.41
     algorithm
    0.41
     MainWindow
    0.40
     convexes
    0.40
     circunfer
    0.40
    Activations Density 0.000%

    No Known Activations