© 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. 78064
    Prev
    Next
    INDEX
    Explanations

    Latvian soprano

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

    Generating recommendations

    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
     distinguishers
    0.53
     dilutions
    0.48
     ductility
    0.48
    dilation
    0.47
    saturation
    0.46
     piecewise
    0.46
    centroids
    0.46
     expediency
    0.46
    damping
    0.46
    뛴
    0.46
    POSITIVE LOGITS
    www
    0.52
    )
    0.49
    ]);
    0.48
     Inland
    0.47
     Galleria
    0.47
    віт
    0.47
    ığını
    0.47
    witter
    0.46
    电话
    0.46
    持有
    0.46
    Activations Density 0.001%

    No Known Activations