© 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. 22-GEMMASCOPE-RES-131K
    7. 72981
    Prev
    Next
    INDEX
    Explanations

    order items in lists

    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_22/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
    端に
    -1.00
     (“
    -1.00
     impe
    -0.94
     decoradas
    -0.93
    Opportunity
    -0.92
    いても
    -0.90
     Svar
    -0.89
    頻繁
    -0.88
     dach
    -0.87
     dedica
    -0.87
    POSITIVE LOGITS
     from
    2.20
     ordenó
    1.36
     ordered
    1.30
     Ordering
    1.30
     hebat
    1.16
    Ordering
    1.16
     suceso
    1.14
     سفارش
    1.13
     order
    1.12
     Ordered
    1.10
    Activations Density 0.021%

    No Known Activations