© 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. 129842
    Prev
    Next
    INDEX
    Explanations

    author;ordomain;

    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
     a
    -1.19
     action
    -1.13
     strategic
    -1.12
     asks
    -1.10
    chyma
    -1.08
     his
    -1.06
     Kooperation
    -1.05
     schreck
    -1.05
     kill
    -1.04
     pessoas
    -1.02
    POSITIVE LOGITS
     saluto
    1.20
    :'',
    1.20
     åren
    1.16
     hende
    1.16
    觥
    1.09
    Simp
    1.09
     compréhension
    1.07
     Reformation
    1.06
    Prag
    1.06
    :"",
    1.05
    Activations Density 0.127%

    No Known Activations