© 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. 75330
    Prev
    Next
    INDEX
    Explanations

    Georgia (GA)

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

    description and explanation

    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
     columnar
    0.43
    으로서
    0.43
     недостаточно
    0.42
    )
    0.39
    \}
    0.39
    5
    0.39
     сда
    0.38
    \}_{
    0.38
     spasm
    0.38
    3
    0.38
    POSITIVE LOGITS
    Aaj
    0.57
     Lehenga
    0.55
    erreur
    0.54
     Sabtu
    0.51
    Juventus
    0.50
    Xbox
    0.49
    accès
    0.49
     İç
    0.49
     Kanye
    0.48
     Rabu
    0.48
    Activations Density 0.001%

    No Known Activations