© 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. 107806
    Prev
    Next
    INDEX
    Explanations

    temperatures

    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
     already
    -0.81
    domain
    -0.81
    *>(
    -0.77
     уже
    -0.77
    렬
    -0.75
    ígenes
    -0.73
    のサ
    -0.73
    Ent
    -0.73
    isantes
    -0.73
     jendela
    -0.73
    POSITIVE LOGITS
     soğ
    0.85
     cold
    0.85
     encou
    0.77
    urop
    0.77
     steven
    0.76
     refrigerate
    0.74
     afo
    0.74
     arthur
    0.74
    Latvia
    0.73
     aar
    0.73
    Activations Density 0.020%

    No Known Activations