© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90889
    Prev
    Next
    INDEX
    Explanations

    official positions and titles

    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
     VISTA
    -0.84
    enteric
    -0.83
     Banten
    -0.82
    دست
    -0.82
    вного
    -0.82
    KOV
    -0.81
    HHH
    -0.81
    Literat
    -0.79
    豋
    -0.78
    ユ
    -0.77
    POSITIVE LOGITS
     Director
    1.84
     Assistant
    1.70
     Chief
    1.66
     Deputy
    1.64
     director
    1.51
     chief
    1.39
     Joint
    1.39
     Senior
    1.37
     Additional
    1.36
     Secretary
    1.31
    Activations Density 0.014%

    No Known Activations