© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73858
    Prev
    Next
    INDEX
    Explanations

    what is the

    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
     завжди
    -1.02
     всегда
    -0.94
    というわけで
    -0.90
     always
    -0.86
    最近は
    -0.85
    下記
    -0.84
    おまけ
    -0.84
    長期
    -0.84
     製
    -0.84
    Always
    -0.84
    POSITIVE LOGITS
    rrrr
    1.00
    eeee
    0.92
     deadline
    0.92
     rå
    0.91
    getMax
    0.85
    pfung
    0.85
     URL
    0.85
     sys
    0.85
     LCD
    0.84
     halb
    0.84
    Activations Density 0.032%

    No Known Activations