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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 119029
    Prev
    Next
    INDEX
    Explanations

    number, identification, quantity

    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
    时间
    -0.92
     ३
    -0.91
     time
    -0.88
    情報
    -0.86
     простой
    -0.84
     Fotos
    -0.81
    kung
    -0.81
    한
    -0.80
     somma
    -0.79
     伊
    -0.75
    POSITIVE LOGITS
     of
    1.25
    enderror
    1.03
     identificación
    0.87
     serializer
    0.86
     psicología
    0.86
     identificação
    0.85
     expediente
    0.83
     Shand
    0.82
     IMEI
    0.82
     îns
    0.81
    Activations Density 0.015%

    No Known Activations