© 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. 11201
    Prev
    Next
    INDEX
    Explanations

    names and qualities

    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
     मुसलमानों
    0.52
    🥵
    0.52
    🤪
    0.49
     blobs
    0.49
     intestin
    0.48
     blob
    0.47
    🐽
    0.47
    😱
    0.47
     బాధ
    0.46
    🤯
    0.46
    POSITIVE LOGITS
     River
    0.46
     Trinity
    0.45
     June
    0.44
     April
    0.44
    Grey
    0.43
     Grey
    0.43
     Rivers
    0.43
     Gray
    0.43
     Juniper
    0.43
     Maverick
    0.42
    Activations Density 0.020%

    No Known Activations