© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67667
    Prev
    Next
    INDEX
    Explanations

    opponent

    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
    N
    -2.98
    c
    -2.77
     '
    -2.72
    ”
    -2.66
    }$
    -2.61
    of
    -2.53
    『
    -2.52
     assorted
    -2.38
    on
    -2.36
    archiwizowane
    -2.34
    POSITIVE LOGITS
    
    2.95
    塍
    2.80
    ſelf
    2.69
    crizione
    2.63
    淠
    2.59
    そういえば
    2.59
    xvii
    2.56
    ⢎
    2.55
    ikusbot
    2.55
     BRARY
    2.52
    Activations Density 0.003%

    No Known Activations