© 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. 127917
    Prev
    Next
    INDEX
    Explanations

    will see, the wedding, the right, read a

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

    state or concept

    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
    시다
    0.46
    టో
    0.46
    டம்
    0.45
    ᑲ
    0.43
    브
    0.43
    ებ
    0.42
    니까
    0.42
    useum
    0.41
    作品
    0.40
    èg
    0.40
    POSITIVE LOGITS
    }.",
    0.52
    বিহীন
    0.50
     EMAIL
    0.47
     oleh
    0.46
    Bootstrap
    0.46
     രാഷ്ട്രീയ
    0.46
     nilai
    0.45
     যৌথ
    0.45
    ."[
    0.45
     causal
    0.45
    Activations Density 0.000%

    No Known Activations