© 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. 27364
    Prev
    Next
    INDEX
    Explanations

    verbs of saying

    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
     and
    -1.11
    ஃ
    -1.07
     लगभग
    -1.05
     emporio
    -1.04
     silencioso
    -1.02
    comparing
    -1.00
    šní
    -0.99
     называют
    -0.99
    💟
    -0.96
    れています
    -0.94
    POSITIVE LOGITS
     further
    1.30
     the
    1.07
     será
    1.06
     will
    1.03
     since
    1.03
     догово
    1.00
     permesso
    0.98
     addition
    0.96
     while
    0.94
     со
    0.94
    Activations Density 0.003%

    No Known Activations