© 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. 90461
    Prev
    Next
    INDEX
    Explanations

    assisting theseen themaking themtold the

    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
     a
    -1.43
     those
    -1.06
     Eigentü
    -1.05
     Wohnungen
    -1.05
     éstas
    -1.02
     their
    -1.01
     jenen
    -0.98
    喟
    -0.97
     denselben
    -0.97
    だそうです
    -0.96
    POSITIVE LOGITS
     the
    3.81
     The
    2.05
    The
    1.40
    咔
    1.19
    addComponent
    1.12
     ofthe
    1.07
    OfThe
    1.00
    ˃
    0.99
     guerra
    0.98
    льо
    0.93
    Activations Density 0.506%

    No Known Activations