© 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. 109574
    Prev
    Next
    INDEX
    Explanations

    code declarations and attributes

    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
     Toyota
    -0.96
     vann
    -0.84
    和谐
    -0.84
    jinal
    -0.82
    ():
    -0.82
     موبایل
    -0.81
    咂
    -0.79
    cA
    -0.78
     една
    -0.76
    ：
    -0.76
    POSITIVE LOGITS
    扬
    0.82
    Bitter
    0.81
     Kolo
    0.77
     WARN
    0.77
     defa
    0.77
     Vordergrund
    0.76
     Lilli
    0.75
    Mamma
    0.75
    Mund
    0.75
    ASUS
    0.75
    Activations Density 0.003%

    No Known Activations