© 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. 10-GEMMASCOPE-RES-131K
    7. 11417
    Prev
    Next
    INDEX
    Explanations

    consent and permission

    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
     ayudarte
    -1.39
     At
    -1.32
     ofrecerte
    -1.30
     fijar
    -1.30
     Ahnung
    -1.29
     potrebné
    -1.28
     hornear
    -1.28
     Änderung
    -1.27
     sekarang
    -1.27
    jące
    -1.25
    POSITIVE LOGITS
     coincident
    1.46
    来自于
    1.45
    despite
    1.32
     parseFrom
    1.30
     ་
    1.27
    んびり
    1.27
    楽しめます
    1.27
     huit
    1.24
     permission
    1.23
    リの
    1.22
    Activations Density 0.102%

    No Known Activations