© 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. 119782
    Prev
    Next
    INDEX
    Explanations

    foundation or grants

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

    contradicts, security, confirmation, align

    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
    خ
    0.54
    غ
    0.44
    ف
    0.44
    latency
    0.42
    显示
    0.41
    ی
    0.40
    وك
    0.40
    大
    0.40
    高速
    0.40
     سین
    0.39
    POSITIVE LOGITS
     Terrier
    0.54
    ñal
    0.53
    Coref
    0.52
     Housewives
    0.51
     तेरा
    0.50
     Tuti
    0.50
     Prison
    0.49
    ждествен
    0.49
    hearted
    0.49
     Jesus
    0.47
    Activations Density 0.000%

    No Known Activations