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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 7328
    Prev
    Next
    INDEX
    Explanations

    javascript module paths

    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
    웅
    -0.91
     новым
    -0.82
     ktor
    -0.82
    øy
    -0.81
     avena
    -0.80
     terminal
    -0.80
    🏎
    -0.78
     櫻
    -0.78
     новые
    -0.77
    conv
    -0.77
    POSITIVE LOGITS
    ͨ
    0.74
    isObject
    0.74
    ipient
    0.74
    fails
    0.73
    GOP
    0.73
     Nm
    0.72
    Naphthalene
    0.71
    boda
    0.70
    virano
    0.70
     delicado
    0.70
    Activations Density 0.043%

    No Known Activations