© 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. 81491
    Prev
    Next
    INDEX
    Explanations

    edited texts and times

    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
    ++
    -0.92
    gradable
    -0.84
    ومه
    -0.82
     presso
    -0.79
    )=>{
    -0.78
     Welle
    -0.78
    🧂
    -0.77
    SIZES
    -0.77
     Tasse
    -0.76
    一路
    -0.76
    POSITIVE LOGITS
     reason
    1.17
    Reason
    1.13
     razão
    1.05
     razón
    1.05
    的原因
    1.04
     perché
    1.02
    理由
    0.99
     reasons
    0.99
     edit
    0.98
    reason
    0.98
    Activations Density 0.009%

    No Known Activations