© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 145265
    Prev
    Next
    INDEX
    Explanations

    This is, your doctor

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

    CLIP, importance, deterministic, plants

    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
     pursuing
    0.47
    bart
    0.44
    frist
    0.44
     barrage
    0.43
     completing
    0.42
    PTO
    0.42
     for
    0.42
    ”
    0.42
     [],
    0.41
    ميم
    0.41
    POSITIVE LOGITS
     प्लांट्स
    0.50
     размещения
    0.50
     лен
    0.49
     ஆராய்ச்சிய
    0.47
     реда
    0.46
     галу
    0.46
     края
    0.45
     наход
    0.44
    츨
    0.44
     пояс
    0.44
    Activations Density 0.002%

    No Known Activations