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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111720
    Prev
    Next
    INDEX
    Explanations

    past or present time references

    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_10/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
     for
    -1.77
     khusus
    -1.59
     gedurende
    -1.55
     legado
    -1.52
    
    -1.51
     Hvis
    -1.48
    <td>
    -1.45
     catálogo
    -1.44
    НТ
    -1.44
     özellikle
    -1.41
    POSITIVE LOGITS
    8
    1.93
    B
    1.76
    7
    1.71
    5
    1.69
    ឵
    1.66
    9
    1.66
    )
    1.61
    ごちそうさまでした
    1.52
     ditt
    1.52
    The
    1.51
    Activations Density 0.011%

    No Known Activations