© 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. 115737
    Prev
    Next
    INDEX
    Explanations

    affecting conditions and outcomes

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

    explaining open weights and values

    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
    佗
    0.49
    เดินทาง
    0.47
    を生
    0.47
    ਰ
    0.47
     teddy
    0.47
     של
    0.46
     vreau
    0.46
    ર્મા
    0.46
     negar
    0.45
     অর্ধেক
    0.45
    POSITIVE LOGITS
     іх
    0.57
    ί
    0.46
    %';
    0.42
    lucene
    0.41
    𒆪
    0.41
    ύ
    0.41
     Employment
    0.40
    ют
    0.40
    ନ୍
    0.40
     Hollande
    0.39
    Activations Density 0.001%

    No Known Activations