© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83089
    Prev
    Next
    INDEX
    Explanations

    technical identifiers and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     even
    -1.27
    ˂
    -1.05
    
    -1.05
    JAMIN
    -1.04
     coronel
    -1.03
    ！）
    -1.02
    
    -0.94
     berpikir
    -0.93
    #(
    -0.93
    حق
    -0.92
    POSITIVE LOGITS
     predominantly
    1.25
     alcune
    1.23
     delightfully
    1.20
    0
    1.20
     этих
    1.19
     decidedly
    1.16
     exceptionally
    1.16
     alcuni
    1.12
     Dinas
    1.09
     and
    1.05
    Activations Density 0.023%

    No Known Activations