© 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. 202349
    Prev
    Next
    INDEX
    Explanations

    leaving a 2cm border

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

    creating/mythology/txt

    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
     تحليل
    0.51
     احتيا
    0.47
     expedit
    0.47
     القر
    0.46
     تنفيذ
    0.46
     practicable
    0.45
    ǵ
    0.45
     تقسيم
    0.45
     defList
    0.45
     boje
    0.45
    POSITIVE LOGITS
    année
    0.51
    use
    0.50
    Ange
    0.50
    tembre
    0.50
    using
    0.49
    Use
    0.48
    ARI
    0.48
    Ş
    0.48
    ätt
    0.46
    тива
    0.46
    Activations Density 0.000%

    No Known Activations