© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 222860
    Prev
    Next
    INDEX
    Explanations

    languages and nationalities

    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
    Ꮧ
    0.46
    уса
    0.42
     noastră
    0.40
    আমাদের
    0.39
     ущер
    0.39
    근
    0.39
    ໄ
    0.39
    дм
    0.39
     bande
    0.38
     pá
    0.37
    POSITIVE LOGITS
     menget
    0.41
     sahab
    0.39
     Germans
    0.36
    蛋白
    0.35
     lettres
    0.35
    ClNO
    0.34
    ICY
    0.34
    હાસ
    0.34
     Spanish
    0.34
     spolu
    0.34
    Activations Density 0.004%

    No Known Activations