© 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. 182185
    Prev
    Next
    INDEX
    Explanations

    has two

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

    diseases and specific entities

    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
    的分
    0.48
     Sessions
    0.48
     Shots
    0.48
    部位
    0.46
    蕃
    0.46
    ляет
    0.45
    莓
    0.45
    的海
    0.44
    的時間
    0.44
     Strateg
    0.44
    POSITIVE LOGITS
    snackbar
    0.45
    wapV
    0.45
     stride
    0.45
    ஹீ
    0.44
    avacanam
    0.44
     extrapolation
    0.44
    iellement
    0.44
     hilar
    0.44
    ᴋ
    0.44
    onk
    0.43
    Activations Density 0.001%

    No Known Activations