© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118624
    Prev
    Next
    INDEX
    Explanations

    license, 5, same, %, type, reach, feet

    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
     this
    -0.96
    มา
    -0.79
     congratulations
    -0.76
    文字
    -0.75
     their
    -0.72
     all
    -0.71
    getUrl
    -0.71
    ク
    -0.71
     starts
    -0.70
     previous
    -0.69
    POSITIVE LOGITS
     alho
    1.00
    feet
    0.89
     applau
    0.86
     feet
    0.85
     psychi
    0.85
     pommes
    0.84
     sonde
    0.84
     Feet
    0.84
     poire
    0.82
    uploads
    0.81
    Activations Density 0.003%

    No Known Activations