© 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. 153688
    Prev
    Next
    INDEX
    Explanations

    irish moss

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

    hover mouse

    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
    ل
    0.61
    ěž
    0.52
    ל
    0.47
    厨
    0.46
    žil
    0.46
    有一种
    0.46
     يق
    0.45
    这是一个
    0.45
    م
    0.45
     إذا
    0.45
    POSITIVE LOGITS
     बनाएंगे
    0.57
     절대
    0.48
     MBE
    0.46
     PARTIC
    0.46
    ເມ
    0.46
    CRR
    0.44
     waven
    0.44
     ಏ
    0.44
     Cnemidophorus
    0.44
     生地
    0.43
    Activations Density 0.000%

    No Known Activations