© 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. 82624
    Prev
    Next
    INDEX
    Explanations

    AI safety disclaimer

    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
    Negative Logits
    ्राफी
    0.43
    če
    0.42
     treffen
    0.42
     ወቅ
    0.41
     köpek
    0.40
    <unused22>
    0.39
     sarkar
    0.39
     चाय
    0.39
     modelu
    0.39
     değerli
    0.39
    POSITIVE LOGITS
    z
    0.47
    NEW
    0.45
    ABC
    0.45
     ABC
    0.44
    FA
    0.43
    procedure
    0.43
    రూ
    0.43
    check
    0.42
    oc
    0.42
    GPS
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.