© 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. 83358
    Prev
    Next
    INDEX
    Explanations

    supported video formats

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

    documentation and history

    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
     Obit
    0.54
     健康
    0.53
    ෞ
    0.52
    PerTrial
    0.51
    {}{
    0.50
    {}",
    0.49
    FTWARE
    0.49
     gewähr
    0.49
    𝐘
    0.49
    Ң
    0.48
    POSITIVE LOGITS
     drastic
    0.58
     provved
    0.57
     steep
    0.52
     by
    0.52
    up
    0.49
    egn
    0.49
     corner
    0.49
    now
    0.48
    by
    0.47
     ditch
    0.47
    Activations Density 0.000%

    No Known Activations