© 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. 166451
    Prev
    Next
    INDEX
    Explanations

    Monte Carlo, asylum seekers

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

    Training vs. Inference

    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
     hetzelfde
    0.49
     Boul
    0.46
     chante
    0.46
    ⴼ
    0.45
     defiance
    0.44
     szere
    0.43
     éléments
    0.42
    ៩
    0.42
    半径
    0.41
    侔
    0.41
    POSITIVE LOGITS
    overview
    0.52
     Gia
    0.51
    Yeni
    0.50
    agment
    0.50
    apia
    0.50
    Enum
    0.49
    quinolin
    0.47
    K
    0.46
    Menu
    0.46
    interaction
    0.46
    Activations Density 0.000%

    No Known Activations