© 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. 240651
    Prev
    Next
    INDEX
    Explanations

    skincare and tropical descriptions

    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
    ذلك
    0.50
     ауди
    0.46
     К
    0.46
     ذلك
    0.46
    ティー
    0.45
    ги
    0.44
    писание
    0.44
     Мол
    0.44
    拶
    0.43
     Ки
    0.43
    POSITIVE LOGITS
    ry
    0.48
    ouard
    0.47
    worker
    0.46
    roit
    0.44
    orts
    0.43
     efficacious
    0.42
     vectorize
    0.42
    rie
    0.42
    ۽
    0.41
     नया
    0.41
    Activations Density 0.000%

    No Known Activations