© 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. 90571
    Prev
    Next
    INDEX
    Explanations

    prevent damage, prohibiting reproduction, satisfied with

    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
     intric
    -1.47
    .~\
    -1.47
     remarquer
    -1.45
    liang
    -1.43
     associés
    -1.43
    ilité
    -1.42
     patate
    -1.41
     expliquer
    -1.41
     traduc
    -1.39
     construit
    -1.38
    POSITIVE LOGITS
     and
    2.52
    Those
    2.14
     what
    2.14
    Perhaps
    1.80
    Both
    1.80
     something
    1.80
     or
    1.78
    Numerous
    1.72
    Unlike
    1.69
    When
    1.67
    Activations Density 0.527%

    No Known Activations