© 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. 234324
    Prev
    Next
    INDEX
    Explanations

    or least

    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
    弥
    0.61
    彌
    0.52
    摑
    0.50
    なか
    0.50
    街道
    0.47
     Sparkling
    0.44
     ऐतिहासिक
    0.43
     Anatom
    0.43
    Dom
    0.43
     Proced
    0.42
    POSITIVE LOGITS
    tbLabel
    0.56
    $=
    0.44
     regretted
    0.43
     happened
    0.42
     apprehended
    0.42
     ஈடுபட்ட
    0.42
     objected
    0.42
     denounced
    0.41
     enjoined
    0.41
    $.)
    0.41
    Activations Density 0.001%

    No Known Activations