© 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. 90001
    Prev
    Next
    INDEX
    Explanations

    directions and measurements

    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
    ક્ટ
    0.49
     stressors
    0.48
    缁
    0.48
    éraux
    0.47
     ৭৮
    0.47
    ОВ
    0.46
    丂
    0.46
    ਗ
    0.45
    であれば
    0.45
    ，
    0.45
    POSITIVE LOGITS
     novi
    0.43
     Eug
    0.41
     Sudah
    0.41
     sudah
    0.40
     stagione
    0.40
     زندہ
    0.39
     Boston
    0.38
     Januari
    0.38
     redan
    0.38
     lưng
    0.38
    Activations Density 0.002%

    No Known Activations