© 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. 33558
    Prev
    Next
    INDEX
    Explanations

    We and our actions

    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
    ští
    -0.83
     deres
    -0.79
     not
    -0.78
     dips
    -0.78
     самого
    -0.75
     deren
    -0.75
    他们
    -0.74
    Ử
    -0.72
    ־
    -0.71
    Arrays
    -0.70
    POSITIVE LOGITS
     داشتند
    1.02
    iscus
    0.99
     любит
    0.96
     team
    0.95
     together
    0.94
    タワー
    0.92
    équipe
    0.90
    Océ
    0.90
     collective
    0.89
    ();*/
    0.88
    Activations Density 0.078%

    No Known Activations