© 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. 60632
    Prev
    Next
    INDEX
    Explanations

    conducted using parliamentary method

    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
     Plan
    -0.81
     plan
    -0.74
     Alex
    -0.69
    Plan
    -0.68
    DETAILED
    -0.66
    lieri
    -0.65
     Planning
    -0.65
     informant
    -0.65
     Java
    -0.64
     helt
    -0.64
    POSITIVE LOGITS
    rads
    0.70
     gobiernos
    0.70
    веси
    0.69
     getBy
    0.69
     Maje
    0.68
    MAKING
    0.67
     Mutable
    0.65
    ু
    0.65
    成績
    0.65
    UFF
    0.65
    Activations Density 0.128%

    No Known Activations