© 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-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138298
    Prev
    Next
    INDEX
    Explanations

    Hebrew names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vagas
    0.39
    Sections
    0.38
    Fuck
    0.38
    cry
    0.38
    Cry
    0.38
    ര്യ
    0.38
    泡
    0.38
     Cry
    0.37
    寄
    0.37
     सैन
    0.36
    POSITIVE LOGITS
     Jewish
    0.89
     Israeli
    0.88
     Israelis
    0.82
     Hebrew
    0.82
    Jewish
    0.81
     Shabbat
    0.80
     Negev
    0.78
     Knesset
    0.75
    Israeli
    0.74
     Talmud
    0.73
    Activations Density 0.001%

    No Known Activations