© 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. 40-GEMMASCOPE-2-RES-262K
    7. 222045
    Prev
    Next
    INDEX
    Explanations

    one, my, updating, DEM

    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_40_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
     पुरुषों
    0.44
     prostitutes
    0.42
     dilutions
    0.41
    ْنَ
    0.41
     petitioners
    0.41
     secondNumber
    0.41
     viscose
    0.40
    LOADSTRING
    0.40
     finalists
    0.40
     TLabel
    0.40
    POSITIVE LOGITS
     جائز
    0.43
    роятно
    0.39
    医学
    0.37
     Penit
    0.36
    building
    0.36
     لیاقت
    0.35
     മത
    0.35
     mỹ
    0.34
    咨
    0.34
    technik
    0.34
    Activations Density 0.000%

    No Known Activations