© 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. 28213
    Prev
    Next
    INDEX
    Explanations

    an amazing, be located

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

    risk and income trade-offs

    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
     einfachen
    0.48
    𝙩
    0.45
     genoeg
    0.44
     cobert
    0.43
     timid
    0.43
    followed
    0.43
    গিরই
    0.42
    在那里
    0.42
    轻轻
    0.42
     francisco
    0.42
    POSITIVE LOGITS
     (\"
    0.51
     }{
    0.47
     consequências
    0.44
     ("
    0.44
     („
    0.44
     (
    0.42
    CO
    0.41
     ${
    0.41
     (\
    0.41
    Ink
    0.41
    Activations Density 0.000%

    No Known Activations