© 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. 34-GEMMASCOPE-RES-131K
    7. 58885
    Prev
    Next
    INDEX
    Explanations

    code access modifiers

    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_34/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
     Sieben
    -0.85
     through
    -0.84
     UNIVE
    -0.82
    missions
    -0.81
    daemon
    -0.81
    Akt
    -0.81
     Uniwers
    -0.79
    liebe
    -0.79
     pasukan
    -0.79
     CommonModule
    -0.78
    POSITIVE LOGITS
    private
    1.27
     a
    1.20
     private
    0.97
     void
    0.89
     privaten
    0.84
     thôi
    0.82
    Btn
    0.82
    一個
    0.80
     privé
    0.80
    ′-
    0.80
    Activations Density 0.001%

    No Known Activations