© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 131045
    Prev
    Next
    INDEX
    Explanations

    Bible, Moon, usually

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

    foreign words and contrasts

    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
    .
    0.61
    َي
    0.45
     الطل
    0.43
     التط
    0.41
    ↵
    0.41
     offenses
    0.40
     وقف
    0.39
     çar
    0.39
    غي
    0.38
     orders
    0.38
    POSITIVE LOGITS
     Usually
    0.54
    焜
    0.48
     Each
    0.47
    During
    0.46
    Antoine
    0.46
    ᾧ
    0.46
     Typically
    0.46
    Although
    0.45
     During
    0.45
     Obviously
    0.45
    Activations Density 0.002%

    No Known Activations