© 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. 25466
    Prev
    Next
    INDEX
    Explanations

    locations of events

    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
     =
    -1.15
    Bjs
    -1.09
    <bos>
    -1.07
    daction
    -1.06
     powy
    -1.02
     cualquier
    -1.01
     $
    -1.00
     cuatro
    -0.98
    _
    -0.98
    overall
    -0.97
    POSITIVE LOGITS
     their
    1.54
     on
    1.36
     in
    1.16
    -|-
    1.15
     home
    1.07
     mereka
    1.05
    Portale
    0.96
    
    0.95
     CardView
    0.94
    getBounds
    0.93
    Activations Density 0.024%

    No Known Activations