© 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. 47300
    Prev
    Next
    INDEX
    Explanations

    points off turnovers

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

    driving vehicles

    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
    ವ
    0.43
    ლ
    0.43
    Sku
    0.41
    Vý
    0.40
    Replacing
    0.40
     말투
    0.40
     platforms
    0.39
    समोर
    0.39
     требуется
    0.38
    Chaos
    0.38
    POSITIVE LOGITS
     Gallagher
    0.47
     wouldn
    0.47
     Berger
    0.45
     মহিলাদের
    0.45
     wouldnt
    0.44
     Vinegar
    0.43
    陏
    0.43
     would
    0.43
    frac
    0.42
     Mobile
    0.42
    Activations Density 0.000%

    No Known Activations