© 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. 54262
    Prev
    Next
    INDEX
    Explanations

    citations and conjunctions

    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
    3
    -1.87
    4
    -1.86
    5
    -1.76
    $
    -1.75
    8
    -1.67
    7
    -1.61
    9
    -1.58
    0
    -1.55
    ans
    -1.53
    all
    -1.51
    POSITIVE LOGITS
     and
    1.94
     vlasy
    1.65
    ventilador
    1.55
    ࿙
    1.52
     because
    1.52
    ขอบคุณ
    1.50
    songs
    1.48
    jelasan
    1.44
    aiuto
    1.44
     podoba
    1.42
    Activations Density 0.008%

    No Known Activations