© 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. 102449
    Prev
    Next
    INDEX
    Explanations

    facial landmarks

    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
    าท
    -0.71
    seck
    -0.68
    basti
    -0.67
    Relevance
    -0.67
    গ্রহ
    -0.66
    glory
    -0.65
     Peep
    -0.65
    はや
    -0.64
     Motivation
    -0.64
    ಫ
    -0.64
    POSITIVE LOGITS
     landmark
    1.60
     landmarks
    1.56
     Landmark
    1.42
    Landmark
    1.31
     Landmarks
    1.20
    landmark
    1.09
    landmarks
    1.03
     LAND
    0.93
    LAND
    0.93
    marks
    0.88
    Activations Density 0.027%

    No Known Activations