© 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. 16610
    Prev
    Next
    INDEX
    Explanations

    foreign language phrases

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

    curious phenomenon

    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
     。
    0.37
     পঞ্চম
    0.36
     r
    0.35
     create
    0.34
    。“
    0.33
    setcounter
    0.33
    သည်။
    0.33
             
    0.33
     ammunition
    0.33
    create
    0.33
    POSITIVE LOGITS
    pesar
    0.43
    quel
    0.40
     samo
    0.40
    rasında
    0.39
    nière
    0.39
    quele
    0.39
    å
    0.39
     ignor
    0.38
     qualunque
    0.38
     tohoto
    0.37
    Activations Density 0.000%

    No Known Activations