© 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. 73494
    Prev
    Next
    INDEX
    Explanations

    Greek pattern, answer any questions

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

    origin from mythology

    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
    mpeg
    0.54
    uš
    0.51
    jších
    0.48
    offs
    0.46
    politik
    0.46
    kde
    0.46
    j
    0.45
    CIS
    0.45
     deh
    0.44
    idmat
    0.44
    POSITIVE LOGITS
    اری
    0.49
    锻炼
    0.46
     luke
    0.46
    𝐔
    0.46
    ції
    0.45
    方
    0.45
    ные
    0.43
    在
    0.43
    梁
    0.42
     in
    0.42
    Activations Density 0.001%

    No Known Activations