© 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. 128857
    Prev
    Next
    INDEX
    Explanations

    address components

    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
     festa
    -1.50
     used
    -1.45
     two
    -1.39
     this
    -1.38
     use
    -1.35
     palestra
    -1.34
     even
    -1.33
     chefe
    -1.31
     would
    -1.29
     Química
    -1.29
    POSITIVE LOGITS
     propriedades
    1.28
    もちゃ
    1.27
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.24
    もしろ
    1.23
    焼く
    1.20
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.20
     offrir
    1.20
     mengikut
    1.20
     fatores
    1.20
     naturels
    1.19
    Activations Density 0.012%

    No Known Activations