© 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. 40898
    Prev
    Next
    INDEX
    Explanations

    guidance and help

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

    help, guidance, and support

    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
     t
    0.56
     ä
    0.52
     u
    0.50
     g
    0.49
     o
    0.47
     chirality
    0.47
     d
    0.47
     be
    0.46
     soldier
    0.46
     has
    0.45
    POSITIVE LOGITS
    createNew
    0.54
    orez
    0.54
     చేయ
    0.53
     మార్
    0.52
    카
    0.52
    с
    0.50
    आप
    0.50
    szön
    0.50
    ответ
    0.49
    kampf
    0.49
    Activations Density 0.000%

    No Known Activations