© 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. 59153
    Prev
    Next
    INDEX
    Explanations

    invitations and requests

    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
     ツ
    -1.21
    Ū
    -1.19
     februari
    -1.09
    🤘
    -1.08
    DDDD
    -1.07
    🤙
    -1.05
    🤯
    -1.05
     januari
    -1.05
    تس
    -1.04
    intrag
    -1.03
    POSITIVE LOGITS
     come
    2.11
     everyone
    1.73
     Come
    1.67
     contact
    1.59
     hope
    1.59
     bring
    1.53
    Come
    1.52
     see
    1.50
     no
    1.41
     call
    1.41
    Activations Density 0.030%

    No Known Activations