© 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. 34-GEMMASCOPE-RES-131K
    7. 92053
    Prev
    Next
    INDEX
    Explanations

    online code examples

    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
    ComponentName
    -0.74
    agent
    -0.73
    FormBuilder
    -0.73
    DEPT
    -0.68
    uyler
    -0.68
    persed
    -0.67
     MOV
    -0.65
     agent
    -0.65
    dhury
    -0.65
    mados
    -0.64
    POSITIVE LOGITS
     düş
    0.64
     Dyer
    0.63
    verley
    0.62
     rincón
    0.62
    ومات
    0.61
    띤
    0.61
    ISD
    0.61
    Bew
    0.59
    حدث
    0.59
    niz
    0.59
    Activations Density 0.055%

    No Known Activations