© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38884
    Prev
    Next
    INDEX
    Explanations

    of/to/in/its followed by noun

    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_22/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
     revela
    -1.17
    麁
    -1.12
     conhecido
    -1.11
     ſaid
    -1.11
    킁
    -1.09
     предлагает
    -1.09
     gleaming
    -1.08
     renowned
    -1.06
     exportaciones
    -1.06
     mejoras
    -1.05
    POSITIVE LOGITS
    ),
    1.05
     katika
    1.03
     is
    1.03
    Törté
    1.02
    }(
    1.02
    ()),
    1.01
    
    0.97
    Air
    0.96
    }(\
    0.95
    ceğine
    0.95
    Activations Density 0.181%

    No Known Activations