© 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. 6932
    Prev
    Next
    INDEX
    Explanations

    programming language declarations

    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
    樖
    0.36
     勺
    0.34
     भैर
    0.33
     Dharmendra
    0.33
     kanamycin
    0.33
     కూడా
    0.32
     pyridine
    0.31
     daisies
    0.31
     expts
    0.30
     norepinephrine
    0.30
    POSITIVE LOGITS
    import
    0.47
    ↵
    0.42
    using
    0.39
    package
    0.38
      
    0.37
    ↵↵
    0.36
    </strong>
    0.33
    java
    0.33
    namespace
    0.33
    <strong>
    0.33
    Activations Density 0.005%

    No Known Activations