© 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. 111384
    Prev
    Next
    INDEX
    Explanations

    sharing life stories

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

    source directory separator ether space

    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
     voitures
    0.61
    ೕ
    0.52
    све
    0.49
     exponencial
    0.47
    鲑
    0.47
    TintMode
    0.46
     recieved
    0.46
     قيم
    0.46
     잘
    0.45
    ivasena
    0.45
    POSITIVE LOGITS
    inen
    0.52
    ด้าน
    0.46
    USB
    0.45
    Bench
    0.43
    OLIS
    0.43
    HD
    0.43
    OL
    0.42
    IA
    0.42
    IRS
    0.42
    April
    0.42
    Activations Density 0.001%

    No Known Activations