© 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. 183721
    Prev
    Next
    INDEX
    Explanations

    trees and shrubs for wildlife

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

    financial ruin or burn

    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
    ү
    0.50
    бра
    0.47
     boilers
    0.46
    cami
    0.45
    ன்கள்
    0.45
    об
    0.45
     líneas
    0.45
    фу
    0.44
    カ
    0.44
    ര്‍
    0.43
    POSITIVE LOGITS
     Delight
    0.44
    饉
    0.43
    🍧
    0.43
    ๋ว
    0.42
     Extrem
    0.42
    ventory
    0.41
     Cartoon
    0.41
    สำหรับการ
    0.41
     Difficult
    0.41
     Exploration
    0.40
    Activations Density 0.003%

    No Known Activations