© 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. 77026
    Prev
    Next
    INDEX
    Explanations

    consists of parts

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

    protagonist, grimace, free entry

    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
    جا
    0.52
    т
    0.49
    탤
    0.48
    転車
    0.47
    р
    0.47
    тэй
    0.47
    håll
    0.46
    이브
    0.46
    拵
    0.46
    ت
    0.45
    POSITIVE LOGITS
     চার
    0.52
    ning
    0.49
     სამ
    0.46
     mathematically
    0.46
    Mathemat
    0.46
     সম
    0.46
    <0xBE>
    0.45
    adoop
    0.45
     পাঁচ
    0.44
    Development
    0.44
    Activations Density 0.001%

    No Known Activations