© 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. 19613
    Prev
    Next
    INDEX
    Explanations

    tensor or vector properties

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

    attention mechanism

    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
    财产
    0.56
    谦
    0.55
     पोलिसा
    0.52
    承认
    0.51
     éton
    0.51
    fitri
    0.51
    荪
    0.51
    俱乐
    0.50
    랄
    0.50
    손
    0.49
    POSITIVE LOGITS
     masks
    0.68
     tensors
    0.67
     logits
    0.66
     cohorts
    0.65
     outputs
    0.64
     softmax
    0.62
     mask
    0.61
     distributions
    0.60
     tensor
    0.59
    logits
    0.59
    Activations Density 0.002%

    No Known Activations