© 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. 108408
    Prev
    Next
    INDEX
    Explanations

    programmatic structure and names

    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
     Supervision
    -0.75
    ueses
    -0.73
     Tot
    -0.73
    fenced
    -0.72
    ⓛ
    -0.71
    ᆹ
    -0.71
     vegetales
    -0.70
    ilingual
    -0.69
     دى
    -0.69
     Anthology
    -0.69
    POSITIVE LOGITS
    Cap
    0.79
    Drivers
    0.78
     }^{\
    0.77
     cap
    0.77
    IPC
    0.77
    翠
    0.77
    MessageInfo
    0.75
    ﻓ
    0.74
    nė
    0.73
    colorbar
    0.73
    Activations Density 0.038%

    No Known Activations