© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9847
    Prev
    Next
    INDEX
    Explanations

    key objectives or challenges

    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_10/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
     líquidos
    -1.61
     dureza
    -1.50
    xvii
    -1.50
     weißt
    -1.48
     angustia
    -1.47
     hiciera
    -1.47
     a
    -1.46
     desplie
    -1.45
     exportación
    -1.45
    étranger
    -1.41
    POSITIVE LOGITS
     of
    2.53
    6
    2.19
    4
    1.97
     will
    1.75
    7
    1.69
     that
    1.68
    2
    1.63
    5
    1.62
    9
    1.60
    8
    1.55
    Activations Density 0.065%

    No Known Activations