© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 140140
    Prev
    Next
    INDEX
    Explanations

    ready to help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    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
    …)
    0.47
     photo
    0.47
    sh
    0.46
     jeep
    0.46
     canoe
    0.46
    Tx
    0.46
    ޯ
    0.46
     wel
    0.45
     instr
    0.45
     Squirrel
    0.45
    POSITIVE LOGITS
    ح
    0.48
    洴
    0.48
    युक्त
    0.47
    деа
    0.47
    油脂
    0.47
    牢
    0.47
    患
    0.46
    焯
    0.46
     tienden
    0.46
    خبار
    0.46
    Activations Density 0.000%

    No Known Activations