© 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. 247500
    Prev
    Next
    INDEX
    Explanations

    completes, complete, construct, support

    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
    ’
    0.55
    '
    0.53
     trường
    0.47
     shouted
    0.47
     matched
    0.43
    
    0.43
    事業
    0.42
    ి
    0.42
     remained
    0.41
    ınca
    0.41
    POSITIVE LOGITS
     Erschein
    0.55
     Wszyst
    0.47
     不是
    0.46
     不能
    0.45
     Gespr
    0.44
    ↵↵↵↵↵↵
    0.44
    নতুন
    0.44
     除了
    0.44
     vorstellen
    0.44
    ినా
    0.43
    Activations Density 0.000%

    No Known Activations