© 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. 47839
    Prev
    Next
    INDEX
    Explanations

    key-value parsing

    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
    licious
    -0.68
     chấp
    -0.67
     нём
    -0.67
     proofs
    -0.66
    amples
    -0.65
    ۓ
    -0.65
     sharp
    -0.65
     valuations
    -0.64
     ¦
    -0.64
     proof
    -0.62
    POSITIVE LOGITS
    ziare
    0.70
    endregion
    0.69
     Gree
    0.69
    ῆ
    0.69
    Cain
    0.69
    ᱱ
    0.68
     BIS
    0.68
    NK
    0.68
    iography
    0.66
    ATO
    0.66
    Activations Density 0.073%

    No Known Activations