© 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. 28918
    Prev
    Next
    INDEX
    Explanations

    increasing something

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

    increased use, debt, risk, scrutiny

    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
    %。
    0.76
    ]।
    0.75
    ]，
    0.75
    ंकन
    0.73
    》。
    0.73
    ]。
    0.71
     ہے۔
    0.69
     этом
    0.68
    ]$,
    0.68
    |$.
    0.67
    POSITIVE LOGITS
    u
    0.91
    t
    0.88
     T
    0.87
     I
    0.82
    ت
    0.76
    is
    0.75
     S
    0.74
     R
    0.74
     F
    0.74
     G
    0.73
    Activations Density 0.046%

    No Known Activations