© 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. 4725
    Prev
    Next
    INDEX
    Explanations

    training and computation specifics

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

    deep learning frameworks and parameters

    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
    谗
    0.79
    蚬
    0.78
    涝
    0.75
    赈
    0.73
    沔
    0.72
    Telephone
    0.72
    袅
    0.71
    观众
    0.71
    荸
    0.71
    觞
    0.70
    POSITIVE LOGITS
     hyperparameters
    1.32
    numpy
    1.16
     numpy
    1.15
     datasets
    1.12
     softmax
    1.11
     preprocessing
    1.08
     scipy
    1.05
     pretrained
    1.05
     computational
    1.04
     vectorized
    1.03
    Activations Density 0.000%

    No Known Activations