© 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. 227293
    Prev
    Next
    INDEX
    Explanations

    but

    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
    0.44
    ↵
    0.44
    ра
    0.42
     просто
    0.41
    Custom
    0.40
    су
    0.38
    ate
    0.37
    Unique
    0.37
     simply
    0.37
    U
    0.36
    POSITIVE LOGITS
     nhưng
    0.82
     lakini
    0.82
     लेकिन
    0.75
     mutta
    0.73
     ولكن
    0.72
     Nhưng
    0.70
     แต่
    0.68
     tetapi
    0.68
     lekin
    0.67
     لیکن
    0.66
    Activations Density 0.005%

    No Known Activations