© 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. 60614
    Prev
    Next
    INDEX
    Explanations

    job offers and roles

    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
     Alfons
    -0.89
     gaf
    -0.86
    vaders
    -0.82
     supli
    -0.80
    POUR
    -0.80
    rów
    -0.79
    ドキドキ
    -0.79
     besø
    -0.79
     subscript
    -0.77
    üman
    -0.77
    POSITIVE LOGITS
     analyst
    1.31
     Analyst
    1.20
    Analyst
    1.07
     Tier
    1.02
     tier
    0.98
     rotations
    0.89
     bulge
    0.88
     Analysts
    0.88
    Modelling
    0.85
     McKinsey
    0.84
    Activations Density 0.035%

    No Known Activations