© 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. 31435
    Prev
    Next
    INDEX
    Explanations

    received / obtained / transfer

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

    AI representation

    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
    efficient
    0.47
    fr
    0.47
    callow
    0.46
    IBM
    0.46
    яд
    0.46
    떠
    0.43
    ορ
    0.42
    ACK
    0.42
    fog
    0.42
    atlantic
    0.41
    POSITIVE LOGITS
     diperoleh
    0.50
     উপরের
    0.50
     devad
    0.49
     telah
    0.48
     belirt
    0.48
     Anche
    0.48
     TRANSFER
    0.48
     obter
    0.48
    🩰
    0.47
     বারবার
    0.46
    Activations Density 0.000%

    No Known Activations