© 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. 249467
    Prev
    Next
    INDEX
    Explanations

    for since

    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
     произведения
    0.47
    劻
    0.45
    ్రు
    0.45
    莧
    0.45
    హ్
    0.45
    рила
    0.45
    ඤ
    0.45
     Jeux
    0.45
    RCB
    0.45
    𝙴
    0.45
    POSITIVE LOGITS
     adversarial
    0.49
     λέ
    0.45
     και
    0.43
     io
    0.41
     vanqu
    0.41
     squarely
    0.40
     αί
    0.40
     built
    0.40
     opaque
    0.39
     dietro
    0.39
    Activations Density 0.002%

    No Known Activations