© 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. 82907
    Prev
    Next
    INDEX
    Explanations

    preposition + identifier

    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
     CELEBR
    -0.95
     良い
    -0.92
     دانلود
    -0.91
    INION
    -0.91
     PROPOSED
    -0.90
    weird
    -0.90
    푅
    -0.89
     LOOKS
    -0.89
    zaak
    -0.88
     embellished
    -0.87
    POSITIVE LOGITS
     using
    1.11
     Tapatalk
    1.10
     an
    1.05
     as
    1.03
     for
    1.03
     at
    1.02
     Using
    0.97
    .$,
    0.96
     cautious
    0.95
     tahap
    0.93
    Activations Density 0.003%

    No Known Activations