© 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. 188473
    Prev
    Next
    INDEX
    Explanations

    designated stop

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

    Provides good answers

    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
     şi
    0.53
    ,"+
    0.51
     و
    0.49
     quando
    0.49
     اسے
    0.49
     lão
    0.49
     کا
    0.48
     Natürlich
    0.48
     Verónica
    0.47
    کراچی
    0.46
    POSITIVE LOGITS
    ov
    0.50
    af
    0.47
     ['',
    0.47
     cref
    0.47
    oS
    0.45
    os
    0.45
     qualifications
    0.45
    ost
    0.44
    ured
    0.44
    uw
    0.42
    Activations Density 0.000%

    No Known Activations