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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3130
    Prev
    Next
    INDEX
    Explanations

    elaborate, enumerate, deliberate

    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
     adhé
    -0.77
     ಮತ್ತು
    -0.75
    cinating
    -0.75
    сур
    -0.75
     Textil
    -0.73
     Cathy
    -0.73
     recognized
    -0.73
    ⴻ
    -0.70
    Richards
    -0.70
     recognise
    -0.69
    POSITIVE LOGITS
    ate
    1.02
    ations
    0.96
    ately
    0.86
    phytes
    0.84
    ateness
    0.83
    ation
    0.81
     판
    0.79
    Hype
    0.79
    APAN
    0.76
    ating
    0.73
    Activations Density 0.027%

    No Known Activations