© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 72666
    Prev
    Next
    INDEX
    Explanations

    scroll down

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

    on a

    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
    在
    0.52
    ￡
    0.51
    ⟢
    0.50
     defend
    0.49
    idez
    0.48
    ￠
    0.48
     popOperand
    0.48
    quando
    0.47
    🫰
    0.47
    OFF
    0.47
    POSITIVE LOGITS
    ەند
    0.42
     ilus
    0.41
     whistling
    0.39
     annoyance
    0.38
     physicists
    0.38
     웨
    0.38
     bulging
    0.38
    чется
    0.38
     애니
    0.38
     enkele
    0.38
    Activations Density 0.000%

    No Known Activations