© 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. 103633
    Prev
    Next
    INDEX
    Explanations

    get something started or somewhere

    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
    canActivate
    -1.05
     búsquedas
    -1.04
    klä
    -1.02
    ұл
    -0.99
     worden
    -0.98
     ngào
    -0.98
    īga
    -0.98
     otrzy
    -0.98
     sellado
    -0.96
     elástico
    -0.95
    POSITIVE LOGITS
     into
    2.67
     to
    2.19
     onto
    1.83
     out
    1.82
     off
    1.30
     started
    1.27
     involved
    1.23
     together
    1.17
     excited
    1.14
    into
    1.08
    Activations Density 0.039%

    No Known Activations