© 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. 80078
    Prev
    Next
    INDEX
    Explanations

    specific reasons, fighting, uses, Lord, airborne

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

    facet reveals

    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
     எனப்படும்
    0.46
    on
    0.45
    ITS
    0.45
    y
    0.44
    Ч
    0.44
    Ди
    0.43
     Laden
    0.41
    Aircraft
    0.41
    다
    0.41
    Ҷ
    0.41
    POSITIVE LOGITS
     glTexParameteri
    0.54
    㦣
    0.50
     سلامه
    0.49
    rières
    0.48
    鋈
    0.47
    န်း
    0.47
     pré
    0.47
    维度
    0.47
    依赖
    0.46
     unabhäng
    0.46
    Activations Density 0.002%

    No Known Activations