© 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. 33269
    Prev
    Next
    INDEX
    Explanations

    music creator, needs, images, ports, age

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

    describing financial concepts

    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
    dib
    0.49
    EN
    0.45
     fucking
    0.45
     温度
    0.44
    echo
    0.44
     深
    0.44
    BF
    0.43
     生成
    0.43
    tib
    0.42
     构建
    0.41
    POSITIVE LOGITS
     واقعات
    0.52
    ormais
    0.50
     loudspeakers
    0.46
     adverts
    0.46
    されていた
    0.46
    heids
    0.45
     receptacles
    0.44
     acontecimientos
    0.44
     primeiras
    0.43
     basaltes
    0.41
    Activations Density 0.000%

    No Known Activations