© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130320
    Prev
    Next
    INDEX
    Explanations

    ability to do something

    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
     estilos
    -1.11
    
    -1.08
     žád
    -1.08
     faciles
    -1.03
     zove
    -1.03
    ͡
    -1.02
     mulighed
    -1.02
     adaptées
    -1.02
     felizes
    -1.02
    daki
    -1.02
    POSITIVE LOGITS
     with
    1.41
     fairly
    1.23
     without
    1.23
     better
    1.22
     reasonably
    1.13
     enough
    1.09
    le
    1.05
     coax
    1.05
     easily
    1.05
     достаточно
    1.04
    Activations Density 0.035%

    No Known Activations