© 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. 227655
    Prev
    Next
    INDEX
    Explanations

    minor compounds

    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
    嘈
    0.51
    坚定
    0.48
    庥
    0.47
    吐槽
    0.46
    坚
    0.46
     està
    0.46
    نتی
    0.45
     Tiny
    0.44
     यासाठी
    0.44
    Chal
    0.44
    POSITIVE LOGITS
    ন্ম
    0.46
    আচ্ছা
    0.45
     製品
    0.44
    ҡ
    0.44
    ᅴ
    0.43
     künstler
    0.42
    一張
    0.42
    タル
    0.42
    Canvas
    0.42
    மைச்சர்
    0.42
    Activations Density 0.001%

    No Known Activations