© 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. 118003
    Prev
    Next
    INDEX
    Explanations

    former or current roles and positions

    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
     Eft
    -0.87
     viszont
    -0.87
    rukt
    -0.85
    STRUCTOR
    -0.84
    衆
    -0.83
     учета
    -0.83
     назвать
    -0.82
     pese
    -0.82
    uples
    -0.82
     freddo
    -0.81
    POSITIVE LOGITS
     Chair
    0.96
     Deputy
    0.91
     Ordinary
    0.85
     Joint
    0.85
     deputy
    0.82
    rendre
    0.80
    Deputy
    0.79
     cross
    0.79
    mô
    0.77
     governors
    0.77
    Activations Density 0.060%

    No Known Activations