© 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. 132001
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    often avoids certain phrasing

    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
     plate
    0.54
     for
    0.54
    ;
    0.54
     forum
    0.51
     bin
    0.49
     son
    0.48
    plate
    0.48
    म
    0.47
    RMS
    0.46
    aps
    0.46
    POSITIVE LOGITS
     συμπ
    0.61
     άνθρω
    0.59
     αυτο
    0.49
     Batterie
    0.49
     verpflichtet
    0.48
     требует
    0.47
     zuerst
    0.47
     Για
    0.47
    বিদেশ
    0.46
     Ευ
    0.46
    Activations Density 0.000%

    No Known Activations