© 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. 217176
    Prev
    Next
    INDEX
    Explanations

    non-English words or specific English occurrences

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

    Kaaba, Risk Level

    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
     ct
    0.53
     ani
    0.51
     permiten
    0.50
     pol
    0.50
     ANI
    0.49
     s
    0.48
     CT
    0.47
     replacing
    0.47
     Ct
    0.47
     CTR
    0.47
    POSITIVE LOGITS
    ك
    0.59
    时间
    0.52
    ق
    0.52
    ้า
    0.52
    غ
    0.51
    上午
    0.50
    هي
    0.50
    日上午
    0.50
    值
    0.49
    伤
    0.48
    Activations Density 0.001%

    No Known Activations