© 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. 109149
    Prev
    Next
    INDEX
    Explanations

    loop counter initialization

    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
     and
    -0.93
    慚
    -0.93
    
    -0.91
     anyway
    -0.90
     tornare
    -0.89
     evitare
    -0.88
     chiare
    -0.86
     rehabilitación
    -0.85
     buone
    -0.85
     rozwiąz
    -0.85
    POSITIVE LOGITS
    ;
    1.62
     ;
    1.04
    ''')
    0.89
    habhar
    0.84
    ftrag
    0.84
    ᱷ
    0.83
    瘪
    0.83
    ;</
    0.83
    蒽
    0.81
     餐
    0.81
    Activations Density 0.009%

    No Known Activations