© 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. 44502
    Prev
    Next
    INDEX
    Explanations

    in your blog post

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

    sharing and collaboration

    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
     chum
    0.50
    드의
    0.49
    철
    0.49
    要
    0.47
    총
    0.46
    입
    0.46
    석
    0.45
     sire
    0.45
    是要
    0.45
    딕
    0.44
    POSITIVE LOGITS
     प्रकाशन
    0.52
     pubblico
    0.45
     جانے
    0.45
     නමුත්
    0.42
     हानि
    0.42
     دینے
    0.42
     langkah
    0.41
     दोषियों
    0.41
     প্রকাশ
    0.40
     کھلاڑی
    0.40
    Activations Density 0.000%

    No Known Activations