© 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. 127117
    Prev
    Next
    INDEX
    Explanations

    material processing

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

    Argentine regional

    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
     धो
    0.51
     CDMA
    0.50
    व
    0.49
    व्य
    0.47
     ナイロン
    0.46
    WERS
    0.46
     सच्चाई
    0.46
    вки
    0.45
     Vn
    0.45
     ratus
    0.45
    POSITIVE LOGITS
     csoport
    0.44
    世
    0.44
     Secular
    0.42
     prone
    0.41
     fournit
    0.41
     programmatic
    0.41
    객
    0.41
     style
    0.41
    对象
    0.41
    驼
    0.40
    Activations Density 0.000%

    No Known Activations