© 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. 203318
    Prev
    Next
    INDEX
    Explanations

    linking ideas and consequences

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

    checklists, guide, server, resources

    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
    ആര്‍
    0.52
     ው
    0.51
     说明
    0.45
    一直在
    0.44
     ناز
    0.43
     intellectuals
    0.42
     perturbation
    0.41
     pulmonary
    0.41
    我很
    0.41
    脨
    0.41
    POSITIVE LOGITS
     Moulton
    0.51
     tha
    0.48
     Chev
    0.48
    '
    0.47
    "
    0.46
     sao
    0.46
    ,
    0.45
    ço
    0.45
     hecho
    0.45
     Bounce
    0.45
    Activations Density 0.001%

    No Known Activations