© 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. 169952
    Prev
    Next
    INDEX
    Explanations

    interest, digital, largest, frank, toxic

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

    speech recognition

    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
    ছিলেন
    0.50
    зу
    0.47
    WhiteBalance
    0.46
    сида
    0.46
    耑
    0.46
    Blockchain
    0.45
    ASH
    0.44
    يش
    0.44
     તેમજ
    0.43
    sacrifice
    0.43
    POSITIVE LOGITS
     Fälle
    0.50
     OMG
    0.47
    >
    0.45
     Ş
    0.45
     Isol
    0.43
     Quin
    0.43
     ۲
    0.43
     Lest
    0.42
    uded
    0.42
     Konz
    0.42
    Activations Density 0.000%

    No Known Activations