© 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. 224578
    Prev
    Next
    INDEX
    Explanations

    organization, test, aircraft, congratulations, kids

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

    existing Content

    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
    Ƅ
    0.47
    setzen
    0.43
    Exercise
    0.42
    re
    0.42
     қ
    0.42
    对外
    0.42
    听
    0.41
    Republic
    0.41
    Dental
    0.41
    贵
    0.41
    POSITIVE LOGITS
     aplicativos
    0.49
     fraude
    0.48
     sociological
    0.47
     marcado
    0.46
     numerosos
    0.45
    зик
    0.45
     ഹാ
    0.45
     servidores
    0.45
     sociétés
    0.44
     referentes
    0.44
    Activations Density 0.001%

    No Known Activations