© 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. 41-GEMMASCOPE-2-RES-262K
    7. 22464
    Prev
    Next
    INDEX
    Explanations

    additional arguments or context

    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_all/layer_41_width_262k_l0_big
    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
    essie
    0.44
    "];
    0.40
    ική
    0.40
    iftet
    0.39
    paired
    0.39
    โม
    0.39
    ปลี่ยน
    0.38
    ineties
    0.38
    linewidth
    0.38
    qualified
    0.38
    POSITIVE LOGITS
     auxili
    0.45
    拒
    0.45
     geri
    0.44
     auxilia
    0.44
     дополнительных
    0.41
     kwargs
    0.41
     inzwischen
    0.41
     zusätz
    0.41
     adicionales
    0.41
     dodat
    0.41
    Activations Density 0.002%

    No Known Activations