© 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. 136735
    Prev
    Next
    INDEX
    Explanations

    beat the market

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

    Vernor Vinge

    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
    ishment
    0.53
    ểm
    0.49
    ତି
    0.48
    iveness
    0.48
    \
    0.47
    umento
    0.47
     як
    0.46
    tainment
    0.46
    midd
    0.46
     necessity
    0.46
    POSITIVE LOGITS
    Xaml
    0.51
     Saltar
    0.49
    கால
    0.47
     Kiara
    0.46
    ापुर
    0.45
    السلام
    0.44
     Facultad
    0.44
    菘
    0.43
     inhab
    0.43
    OAuth
    0.42
    Activations Density 0.000%

    No Known Activations