© 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. 31-GEMMASCOPE-2-RES-262K
    7. 33143
    Prev
    Next
    INDEX
    Explanations

    common concepts and entities

    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_31_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
     migrants
    0.48
    angled
    0.47
    conversion
    0.46
    able
    0.44
    পক্ষের
    0.43
    콥
    0.43
     guests
    0.43
    ninja
    0.42
    mong
    0.42
    engage
    0.41
    POSITIVE LOGITS
    Ге
    0.43
    Servo
    0.41
    Bau
    0.40
    Mater
    0.40
     Pleasant
    0.39
    祝
    0.39
     прият
    0.39
     ζ
    0.39
     वोल्
    0.39
    💖
    0.39
    Activations Density 0.002%

    No Known Activations