© 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. 177706
    Prev
    Next
    INDEX
    Explanations

    specific entities or conditions

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

    food ingredients, graphics programming

    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
     “
    0.46
     Chud
    0.44
    hone
    0.44
     Plummer
    0.44
    aine
    0.44
     antid
    0.44
    circum
    0.44
     Sid
    0.43
    礪
    0.43
     chamb
    0.43
    POSITIVE LOGITS
     ungefähr
    0.50
     ম্যান
    0.46
    reuung
    0.44
     lộ
    0.43
    座椅
    0.43
    之类的
    0.43
     qí
    0.43
     publicación
    0.43
    𝐫
    0.43
     ներ
    0.42
    Activations Density 0.000%

    No Known Activations