© 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. 71141
    Prev
    Next
    INDEX
    Explanations

    when to use

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

    when to use each

    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
     oef
    0.45
    exclude
    0.42
    公演
    0.42
     exame
    0.40
    ogeneous
    0.40
     imposible
    0.40
    جمالي
    0.39
    ฝึก
    0.39
    ］
    0.39
    ্যা
    0.39
    POSITIVE LOGITS
    गुड
    0.43
     someone
    0.43
     Pantry
    0.43
     Worte
    0.42
    тая
    0.41
    ल्लिंग
    0.41
     Stok
    0.41
     Nok
    0.41
    콕
    0.41
    똘
    0.41
    Activations Density 0.001%

    No Known Activations