© 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. 103970
    Prev
    Next
    INDEX
    Explanations

    copyright and license terms

    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
     Colegio
    -0.93
    غه
    -0.89
     nat
    -0.79
     Municipio
    -0.72
     giấc
    -0.71
    roux
    -0.70
     NOTA
    -0.70
    🌖
    -0.70
     Credentials
    -0.69
    ikyuu
    -0.69
    POSITIVE LOGITS
    idp
    0.72
    waża
    0.71
    billion
    0.66
     Съ
    0.66
    Conheça
    0.65
    Nossa
    0.65
     Utd
    0.64
    挑
    0.64
    TimeUnit
    0.64
    AA
    0.63
    Activations Density 0.016%

    No Known Activations