© 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. 67454
    Prev
    Next
    INDEX
    Explanations

    business and university

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

    reframe

    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
     Estudios
    0.52
     Estudos
    0.52
     Estudio
    0.51
     Ciencias
    0.49
    🚧
    0.47
     Modelo
    0.47
    📙
    0.47
     masculino
    0.46
     típico
    0.46
     Estadio
    0.46
    POSITIVE LOGITS
    value
    0.54
    newValue
    0.49
    unction
    0.49
    t
    0.45
    ı
    0.45
    range
    0.45
    price
    0.45
    Value
    0.44
    angle
    0.44
    speed
    0.44
    Activations Density 0.001%

    No Known Activations