© 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. 22-GEMMASCOPE-RES-131K
    4. 13201
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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_22/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
     Once
    -1.86
     If
    -1.84
     Some
    -1.77
     With
    -1.76
     It
    -1.74
     at
    -1.73
     it
    -1.70
     Have
    -1.68
     Make
    -1.68
     There
    -1.65
    POSITIVE LOGITS
    などが
    2.14
    などを
    2.09
     faciliter
    1.88
    <bos>
    1.84
     スリーブ
    1.71
     puissent
    1.68
     pán
    1.67
     offrir
    1.63
    がありますが
    1.61
    iferous
    1.60
    Activations Density 0.076%

    No Known Activations