© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91634
    Prev
    Next
    INDEX
    Explanations

    protected void method definitions

    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
    lož
    -0.75
     ciclista
    -0.75
    melon
    -0.74
    Resizable
    -0.70
     Suggest
    -0.70
     Leah
    -0.70
    PURCHASE
    -0.69
    Suggest
    -0.69
     Schwab
    -0.68
    📋
    -0.68
    POSITIVE LOGITS
    plural
    0.75
     Boa
    0.70
    Opere
    0.69
     do
    0.68
    semi
    0.67
    territ
    0.66
     cảnh
    0.65
     Porcelain
    0.65
    scaffold
    0.65
    前進
    0.65
    Activations Density 0.075%

    No Known Activations