© 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. 18512
    Prev
    Next
    INDEX
    Explanations

    brands and named products

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

    "themed poem" / "our homes" / "beautiful day"

    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
     समान
    0.40
    ㄞ
    0.39
    至於
    0.39
    睪
    0.39
    θεν
    0.38
     عرص
    0.38
    咡
    0.38
     $-\
    0.37
    埸
    0.37
     handouts
    0.37
    POSITIVE LOGITS
     LEGO
    0.69
     HUAWEI
    0.55
     Roblox
    0.53
     emoji
    0.53
     نقدم
    0.52
     crochet
    0.52
     adidas
    0.52
    LEGO
    0.52
     PlayStation
    0.51
     naš
    0.51
    Activations Density 0.311%

    No Known Activations