© 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. 107636
    Prev
    Next
    INDEX
    Explanations

    Italian pope

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

    breakdown of communication

    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
    innerHeight
    0.47
     పరీ
    0.44
    احة
    0.44
    ר
    0.44
     HEP
    0.44
    Aloe
    0.43
     الرحيم
    0.43
     Дру
    0.42
     കരുത
    0.42
     શું
    0.42
    POSITIVE LOGITS
    setHora
    0.46
     literary
    0.45
    ยม
    0.45
    碎
    0.44
    ویی
    0.44
     pilgrimage
    0.42
    weisung
    0.42
     envoy
    0.42
    िसोदिया
    0.42
     magní
    0.41
    Activations Density 0.002%

    No Known Activations