© 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. 73576
    Prev
    Next
    INDEX
    Explanations

    identifying states or characteristics

    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
     ottobre
    -1.35
     heti
    -1.18
     new
    -1.15
     also
    -1.15
     Other
    -1.12
     all
    -1.08
     наук
    -1.07
     his
    -1.06
    paddingBottom
    -1.05
     и
    -1.03
    POSITIVE LOGITS
     Odour
    1.14
    :'',
    1.13
     Deceased
    1.08
    itern
    1.07
     marchio
    1.06
     який
    1.06
    Ошибка
    1.06
    错了
    1.05
     Sickness
    1.05
     Converts
    1.05
    Activations Density 0.084%

    No Known Activations