© 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. 116843
    Prev
    Next
    INDEX
    Explanations

    early detection

    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
    ｀*)
    -0.78
     خواست
    -0.69
     Lut
    -0.69
    lanmış
    -0.69
    ilibr
    -0.69
    pielt
    -0.67
    amment
    -0.67
    囂
    -0.67
    ěl
    -0.66
    lustre
    -0.66
    POSITIVE LOGITS
     detect
    5.25
     detection
    5.16
     detecting
    5.00
     detected
    4.97
     detects
    4.69
    detect
    4.47
     Detection
    4.31
     Detect
    4.25
    Detect
    4.16
    Detection
    4.13
    Activations Density 0.395%

    No Known Activations