© 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. 173182
    Prev
    Next
    INDEX
    Explanations

    looks like or appears

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

    looks like / seems like / appears

    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
     as
    0.55
     veiled
    0.54
     sound
    0.49
     inspect
    0.47
    <0xAE>
    0.46
    我觉得
    0.46
    <0xB8>
    0.45
     imaging
    0.45
     bunları
    0.45
    ت
    0.45
    POSITIVE LOGITS
     очередной
    0.59
    新たな
    0.52
     шанс
    0.50
     успешно
    0.50
     опубликова
    0.50
     принято
    0.50
    دأ
    0.48
    fortunately
    0.48
    spaceship
    0.48
     трёх
    0.47
    Activations Density 0.038%

    No Known Activations