© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40763
    Prev
    Next
    INDEX
    Explanations

    new features and syntax

    np_acts-logits-general · gemini-2.5-flash-lite

    modern programming language features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    もん
    0.45
    砾
    0.43
    两天
    0.43
    ബ്ര
    0.42
    hasFocus
    0.41
    лук
    0.41
    โรค
    0.41
    珞
    0.40
    无限
    0.39
    锋
    0.39
    POSITIVE LOGITS
    babel
    0.59
     transp
    0.52
    syntax
    0.48
     babel
    0.47
    openzeppelin
    0.46
    features
    0.46
    gcd
    0.45
     preset
    0.45
     modernas
    0.44
    enhanced
    0.44
    Activations Density 0.006%

    No Known Activations