© 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. 19907
    Prev
    Next
    INDEX
    Explanations

    Baron / baronet / criteria

    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
    着一个
    -1.75
     semblent
    -1.48
    TestBed
    -1.47
     luffy
    -1.41
     extremely
    -1.36
     amazingly
    -1.34
     apparaissent
    -1.32
    hounds
    -1.31
     zeitung
    -1.29
     jf
    -1.29
    POSITIVE LOGITS
     even
    1.79
     people
    1.69
     only
    1.61
     our
    1.60
    </em>
    1.45
     it
    1.44
    ↵↵↵
    1.44
     their
    1.41
     sogar
    1.40
    detek
    1.39
    Activations Density 0.182%

    No Known Activations