© 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. 111093
    Prev
    Next
    INDEX
    Explanations

    given or presented

    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
    arschu
    -0.86
    Covered
    -0.82
    Solic
    -0.74
    Spent
    -0.72
     Temmuz
    -0.72
    込み
    -0.71
    нні
    -0.71
     declaración
    -0.70
     dispers
    -0.70
    gación
    -0.70
    POSITIVE LOGITS
     handed
    2.36
     presented
    2.33
     bestowed
    2.17
     thrown
    2.13
     assigned
    2.08
     offered
    2.02
     placed
    1.85
     imposed
    1.84
     given
    1.66
    assigned
    1.64
    Activations Density 0.097%

    No Known Activations