© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7343
    Prev
    Next
    INDEX
    Explanations

    value field

    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
     neues
    -1.54
    structing
    -1.39
    #%%
    -1.39
    cisive
    -1.28
     lokale
    -1.28
     certains
    -1.26
     necesar
    -1.26
    !”
    -1.26
    ReferenceEquals
    -1.24
     drei
    -1.23
    POSITIVE LOGITS
    )
    1.44
     value
    1.37
     that
    1.35
    <td>
    1.31
    thiết
    1.29
    sediaan
    1.29
    してみると
    1.26
     who
    1.23
     speichern
    1.23
     bemerken
    1.21
    Activations Density 0.131%

    No Known Activations