© 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. 23493
    Prev
    Next
    INDEX
    Explanations

    code block endings

    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
    return
    -1.12
     this
    -0.96
     "$@"
    -0.83
     dahin
    -0.81
    iction
    -0.81
     but
    -0.81
    $+\
    -0.81
    />,
    -0.79
     whereas
    -0.79
     menjal
    -0.78
    POSITIVE LOGITS
    continue
    1.18
     continue
    1.03
     break
    0.98
     segíts
    0.89
     breaks
    0.88
    endforeach
    0.88
    ச்
    0.87
     endforeach
    0.85
     increasingly
    0.84
    enddo
    0.83
    Activations Density 0.014%

    No Known Activations