© 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. 46159
    Prev
    Next
    INDEX
    Explanations

    prospective, them, ing, Med

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

    dates and minor injuries

    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
     ہم
    0.43
     लीजिए
    0.43
    変数
    0.43
     तप
    0.42
     இந்தப்
    0.42
    閘
    0.41
     superposition
    0.41
     MNIST
    0.41
     XOR
    0.41
    Cra
    0.39
    POSITIVE LOGITS
     onların
    0.45
    💒
    0.45
     ngunit
    0.44
    ívá
    0.42
    🛶
    0.42
     nende
    0.42
     маъ
    0.42
    üedad
    0.42
     hukuk
    0.41
     tendência
    0.41
    Activations Density 0.000%

    No Known Activations