© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13191
    Prev
    Next
    INDEX
    Explanations

    java package declarations

    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
     klip
    -1.14
     ApiClient
    -1.13
     }^{\
    -1.11
     boks
    -1.10
     asti
    -1.09
     roj
    -1.09
     tigre
    -1.09
     paco
    -1.07
    če
    -1.05
     userType
    -1.05
    POSITIVE LOGITS
     Persönlichkeit
    1.33
     gän
    1.32
    botella
    1.25
     Aussehen
    1.23
     Verständnis
    1.21
     zweck
    1.21
     wcześniej
    1.20
     trabajador
    1.19
    うれ
    1.18
     Redewendung
    1.18
    Activations Density 0.000%

    No Known Activations