© 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. 213065
    Prev
    Next
    INDEX
    Explanations

    contacting correspondence pills treats

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

    noun followed by connecting word

    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
     ♡
    0.46
    Blo
    0.45
     daly
    0.44
     revelar
    0.44
     exhilar
    0.43
    ם
    0.43
    LLER
    0.42
     হাট
    0.42
     recevoir
    0.41
     уди
    0.41
    POSITIVE LOGITS
    status
    0.47
    不同的
    0.46
    氏
    0.45
    局部
    0.44
    N
    0.44
    作り
    0.43
    ikey
    0.43
    位数
    0.43
    对比
    0.42
    既然
    0.42
    Activations Density 0.001%

    No Known Activations