© 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-262K
    7. 11673
    Prev
    Next
    INDEX
    Explanations

    precise amounts or specific rules

    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
     Sparrow
    0.52
    ，
    0.45
     Daniel
    0.42
     постепен
    0.42
    为一个
    0.42
    <unused2121>
    0.42
    ،
    0.41
    设计
    0.41
     dần
    0.41
    steak
    0.40
    POSITIVE LOGITS
     racks
    0.47
     motivating
    0.46
     ggtitle
    0.46
    दमी
    0.42
     faid
    0.42
     enjoyment
    0.41
     groan
    0.41
     tired
    0.40
     yielded
    0.40
    trk
    0.40
    Activations Density 0.001%

    No Known Activations