© 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. 159420
    Prev
    Next
    INDEX
    Explanations

    Israeli Palestinian conflict occupation

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

    Israel, Jerusalem, annexation, imprisoned Palestinians

    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
     sở
    0.46
     Strokes
    0.43
     sniff
    0.40
     Hoover
    0.40
    溴
    0.39
     rotary
    0.38
     ஹோ
    0.38
    缪
    0.38
     ڈیز
    0.37
     trustworthiness
    0.37
    POSITIVE LOGITS
    Гор
    0.46
    ôn
    0.41
    container
    0.41
    ikler
    0.40
     незакон
    0.40
    PhotoMode
    0.39
    प्रकाश
    0.39
     Гор
    0.39
    toni
    0.39
     unlawfully
    0.38
    Activations Density 0.052%

    No Known Activations