© 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. 118087
    Prev
    Next
    INDEX
    Explanations

    legal and institutional contexts

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

    reality checks

    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
    у
    0.44
    номи
    0.43
    heritage
    0.43
    ونز
    0.42
    egrave
    0.41
    昃
    0.41
    robe
    0.41
    س
    0.41
    compensation
    0.41
    use
    0.40
    POSITIVE LOGITS
     сва
    0.50
     inserting
    0.45
     света
    0.41
    ljenje
    0.40
     ብ
    0.40
     άλλα
    0.40
     данной
    0.39
     вполне
    0.39
    দ্র
    0.39
     желу
    0.39
    Activations Density 0.001%

    No Known Activations