© 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. 89894
    Prev
    Next
    INDEX
    Explanations

    aged X and above

    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
    uelta
    -0.82
     dispen
    -0.80
    })=
    -0.79
     腕
    -0.78
     قسمت
    -0.77
    caman
    -0.77
    setcounter
    -0.76
    интер
    -0.76
    <td>
    -0.75
    )=
    -0.75
    POSITIVE LOGITS
     above
    3.63
    above
    2.75
     below
    2.69
     выше
    2.55
     beyond
    2.50
     higher
    2.25
    以上
    2.16
     upwards
    2.13
    Above
    2.11
     up
    2.08
    Activations Density 0.050%

    No Known Activations