© 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. 34-GEMMASCOPE-RES-131K
    7. 78206
    Prev
    Next
    INDEX
    Explanations

    date and code variables

    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
     itemName
    -0.96
     зараз
    -0.80
    roleId
    -0.77
     userType
    -0.77
     oeste
    -0.76
     accused
    -0.76
     taskId
    -0.76
    oom
    -0.75
     חיצוני
    -0.75
     nyt
    -0.74
    POSITIVE LOGITS
    Discriminator
    0.99
    cshtml
    0.98
    nvarchar
    0.96
    ")]
    0.95
    FirstOrDefault
    0.95
    ")]
    0.93
    positor
    0.91
    ński
    0.90
    wstring
    0.86
    Concurrency
    0.84
    Activations Density 0.007%

    No Known Activations