© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75853
    Prev
    Next
    INDEX
    Explanations

    or not / with or without

    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
    Če
    -0.96
    																
    -0.88
    ghed
    -0.88
    یفون
    -0.87
    ástico
    -0.87
    χα
    -0.83
    ocarcinoma
    -0.78
    Royce
    -0.78
     тільки
    -0.78
    																	
    -0.77
    POSITIVE LOGITS
    not
    1.08
     or
    0.99
     большей
    0.98
    NOT
    0.98
     may
    0.93
     deton
    0.91
     менее
    0.87
    否
    0.84
     May
    0.81
     not
    0.80
    Activations Density 0.018%

    No Known Activations