© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63158
    Prev
    Next
    INDEX
    Explanations

    company names and product launches

    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
     RER
    -0.80
     banc
    -0.75
     FN
    -0.74
    modities
    -0.73
     sains
    -0.72
    Ȁ
    -0.72
    RER
    -0.72
     manufactured
    -0.71
     pallid
    -0.71
    <0xD0>
    -0.70
    POSITIVE LOGITS
     subscriber
    1.05
     subscribers
    0.85
     tower
    0.80
    substituted
    0.79
     feud
    0.79
    SerializeField
    0.77
     golden
    0.76
     spectral
    0.76
     roaming
    0.76
    ulates
    0.75
    Activations Density 0.014%

    No Known Activations