© 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. 221829
    Prev
    Next
    INDEX
    Explanations

    building products

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

    contrast and explanation

    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
    ir
    0.51
    \-
    0.44
     intersect
    0.44
     parecen
    0.44
    p
    0.44
     ಆಗಿದೆ
    0.43
    deme
    0.43
    op
    0.42
    ↵↵
    0.41
    lg
    0.41
    POSITIVE LOGITS
     счастли
    0.47
     تبدی
    0.46
     دوم
    0.46
    惆
    0.45
     ד
    0.44
     행복
    0.44
     주로
    0.43
     बैंक
    0.42
     റ
    0.42
     सम्बन्ध
    0.42
    Activations Density 0.001%

    No Known Activations