© 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. 27740
    Prev
    Next
    INDEX
    Explanations

    closing punctuation

    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
     rudimentary
    -1.12
     frantic
    -1.09
     should
    -1.09
    ：　
    -1.09
     HUGE
    -1.04
     exuberant
    -1.03
     two
    -1.02
     sparkly
    -1.02
     Those
    -1.00
     spurred
    -1.00
    POSITIVE LOGITS
     остальные
    1.13
     acuerdos
    1.04
    žité
    1.03
    دیگر
    1.00
     naszej
    1.00
     estándares
    0.99
     EAT
    0.98
     andere
    0.98
     kolejne
    0.96
     specif
    0.96
    Activations Density 0.100%

    No Known Activations