© 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. 183512
    Prev
    Next
    INDEX
    Explanations

    between nations and powerful

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

    lists of descriptive categories

    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
     your
    0.56
     organiser
    0.53
    會
    0.52
     you
    0.50
     organisers
    0.49
     chant
    0.48
     organise
    0.48
     會
    0.47
     ‌
    0.47
     ў
    0.46
    POSITIVE LOGITS
     καθώς
    0.57
    িকাংশ
    0.50
    줍니다
    0.49
    ากาศ
    0.47
    izados
    0.47
     الذين
    0.47
    ட்கள்
    0.47
    িলারা
    0.46
    囦
    0.46
    ুয়াল
    0.46
    Activations Density 0.000%

    No Known Activations