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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11537
    Prev
    Next
    INDEX
    Explanations

    bus, bus topology, hardware, signals

    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
     ſtate
    -2.80
    荭
    -2.64
    
    -2.53
    ⟣
    -2.48
    Ꮴ
    -2.48
    胪
    -2.45
    谖
    -2.42
     unſ
    -2.34
    凊
    -2.30
     necessárias
    -2.28
    POSITIVE LOGITS
    \
    2.66
    am
    2.55
    }$
    2.55
     Both
    2.44
    )/
    2.31
    )-
    2.31
    |$.
    2.28
     These
    2.20
    🍻
    2.13
    ຼ
    2.13
    Activations Density 0.011%

    No Known Activations