© 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. 33414
    Prev
    Next
    INDEX
    Explanations

    HTML select option

    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
    falt
    -0.83
    ALT
    -0.82
     Lithium
    -0.78
    닷
    -0.78
    看着
    -0.77
    Authorities
    -0.76
    擅
    -0.76
    Phase
    -0.73
    LAW
    -0.73
     Alternate
    -0.73
    POSITIVE LOGITS
     option
    2.94
    option
    2.42
     Option
    2.16
     options
    1.91
    Option
    1.88
    getOption
    1.67
     opt
    1.65
     OPTION
    1.59
    OPTION
    1.57
     opción
    1.43
    Activations Density 0.009%

    No Known Activations