© 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. 39500
    Prev
    Next
    INDEX
    Explanations

    year, olds, community

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

    context and surrounding text

    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
    ح
    0.57
    ه
    0.52
    tracer
    0.50
    f
    0.50
    ghi
    0.49
    the
    0.48
    टेल
    0.47
    部分
    0.46
    тися
    0.46
    ह
    0.45
    POSITIVE LOGITS
     baños
    0.55
     เอ่อ
    0.54
     są
    0.48
    finaly
    0.48
     obsz
    0.48
     cultivos
    0.47
     Abbiamo
    0.44
     TouchUtils
    0.44
     μεταξύ
    0.43
     উৎস
    0.43
    Activations Density 0.000%

    No Known Activations