© 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. 119262
    Prev
    Next
    INDEX
    Explanations

    assigned value

    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
     sensuous
    -0.87
    anoke
    -0.81
    onne
    -0.80
     bellissima
    -0.79
    رافیک
    -0.76
    annelse
    -0.75
    шений
    -0.74
    一方
    -0.74
    ulur
    -0.73
    keyboard
    -0.73
    POSITIVE LOGITS
     value
    2.59
     Value
    1.81
    value
    1.74
    Value
    1.62
    VALUE
    1.61
    価値
    1.53
     values
    1.53
     valeur
    1.51
    价值
    1.45
     VALUE
    1.38
    Activations Density 0.005%

    No Known Activations