© 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. 33727
    Prev
    Next
    INDEX
    Explanations

    marking new sections

    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
     restes
    -1.32
     remercier
    -1.30
     décisions
    -1.26
     salmón
    -1.23
     Humph
    -1.21
     kumar
    -1.21
    
    -1.19
     varier
    -1.18
     grilling
    -1.18
     нашим
    -1.17
    POSITIVE LOGITS
     has
    1.37
     there
    1.35
     began
    1.15
     before
    1.14
    //!
    1.13
     did
    1.10
    circ
    1.08
     in
    1.06
     told
    1.05
     年轻
    1.05
    Activations Density 0.044%

    No Known Activations