© 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. 129198
    Prev
    Next
    INDEX
    Explanations

    Q: | with | The

    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
    licitations
    -1.24
    ofing
    -1.16
     père
    -1.16
    oused
    -1.15
    
    -1.14
    taker
    -1.13
    urium
    -1.13
    ÑOS
    -1.13
     déjeuner
    -1.13
    ErrorListener
    -1.12
    POSITIVE LOGITS
    entendre
    1.08
     enhancing
    1.07
     additional
    1.04
     continued
    1.03
     unusual
    1.03
    <em>
    1.02
    BEL
    1.01
     immediately
    1.01
     dramatically
    1.01
     increased
    1.00
    Activations Density 0.000%

    No Known Activations