© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6798
    Prev
    Next
    INDEX
    Explanations

    "As a" format for user stories

    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_16k_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
    func
    0.46
    錒
    0.45
     UNITS
    0.45
    ביר
    0.42
    Т
    0.42
    Игра
    0.41
    Wir
    0.41
    Со
    0.41
    事件
    0.41
     Ио
    0.40
    POSITIVE LOGITS
     exudes
    0.41
     less
    0.41
     Visitor
    0.38
     calmer
    0.38
     stroller
    0.37
     inexperienced
    0.37
     visitors
    0.36
    做
    0.36
     under
    0.36
    ines
    0.36
    Activations Density 0.011%

    No Known Activations