© 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. 87355
    Prev
    Next
    INDEX
    Explanations

    subject followed by descriptor or verb

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

    describe appearance or location

    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
    轉換
    0.47
    懂得
    0.46
     रिलेशन
    0.46
    upgrade
    0.45
     مليون
    0.45
     Nobel
    0.44
    蒡
    0.43
     राष्ट्रपति
    0.43
    房子
    0.42
    付出
    0.42
    POSITIVE LOGITS
     pantai
    0.59
     beaches
    0.54
     to
    0.52
     identifying
    0.51
     ♡
    0.50
    स्थल
    0.49
     klingt
    0.49
     descriptors
    0.47
     erz
    0.46
     DESCRIPTION
    0.46
    Activations Density 0.001%

    No Known Activations