© 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. 72013
    Prev
    Next
    INDEX
    Explanations

    Dr

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

    CSS styling

    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
    {
    0.53
     numerosos
    0.52
    gre
    0.51
    Get
    0.50
    gn
    0.50
    mel
    0.48
    gem
    0.48
    drug
    0.48
     numerosas
    0.47
    MM
    0.47
    POSITIVE LOGITS
    璿
    0.51
     ಸಾಮಾನ್ಯವಾಗಿ
    0.50
    ან
    0.50
    作战
    0.46
     Saxon
    0.46
     Biał
    0.46
    ᗜ
    0.46
    ಿದರು
    0.46
     November
    0.44
    講解
    0.44
    Activations Density 0.001%

    No Known Activations