© 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. 117681
    Prev
    Next
    INDEX
    Explanations

    foreign words or mixed text

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

    Interpretation, descriptions, conditions, messages

    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
     Robinson
    0.44
     Riet
    0.44
    ","
    0.42
    发生的
    0.42
     Caroline
    0.42
     مخت
    0.42
     Lazarus
    0.41
     చ
    0.41
    Robinson
    0.41
     المياه
    0.41
    POSITIVE LOGITS
     runga
    0.51
     edhe
    0.49
    キラ
    0.48
    बंग
    0.48
    אם
    0.47
     zada
    0.47
    끙
    0.47
     esigen
    0.47
     остались
    0.46
    풉
    0.46
    Activations Density 0.000%

    No Known Activations