© 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. 31-GEMMASCOPE-2-RES-65K
    7. 50844
    Prev
    Next
    INDEX
    Explanations

    block scraping

    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_65k_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
    truck
    0.45
    점
    0.45
    दूर
    0.45
    !".
    0.43
    것
    0.42
    다음
    0.42
     Slack
    0.41
    대한
    0.40
    á
    0.40
    ногда
    0.40
    POSITIVE LOGITS
    ovalent
    0.46
    lef
    0.46
    >∗</
    0.45
    “-
    0.45
     ဂ
    0.45
    右手
    0.44
    ubat
    0.44
    主要是
    0.44
     عض
    0.44
     συνο
    0.43
    Activations Density 0.002%

    No Known Activations