© 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. 27907
    Prev
    Next
    INDEX
    Explanations

    python, java, c, php, csharp imports

    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
    explain
    0.41
    #
    0.40
    Gd
    0.39
    Compiled
    0.38
    examples
    0.38
    define
    0.38
    üd
    0.37
    this
    0.37
    Lic
    0.37
    babel
    0.36
    POSITIVE LOGITS
     UITableView
    0.45
     OXIDES
    0.42
     جات
    0.39
     drawSprites
    0.39
     courrier
    0.39
     صدا
    0.38
    嚨
    0.38
    溶液
    0.38
    愴
    0.37
     DISPLAYSURF
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.