© 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. 76517
    Prev
    Next
    INDEX
    Explanations

    pass on or to

    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
     bri
    -0.82
    arf
    -0.82
     marsh
    -0.82
    NSF
    -0.80
    lipid
    -0.79
    BRD
    -0.77
     előtt
    -0.77
    Inserted
    -0.76
    Overlap
    -0.75
    isance
    -0.74
    POSITIVE LOGITS
     onto
    2.41
     along
    1.80
     forward
    1.80
     onward
    1.61
     onwards
    1.59
     to
    1.42
    forward
    1.42
     vidare
    1.40
     passed
    1.32
    Along
    1.30
    Activations Density 0.034%

    No Known Activations