© 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. 22-GEMMASCOPE-RES-131K
    7. 68494
    Prev
    Next
    INDEX
    Explanations

    seeking more information or details

    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
    
    -1.19
     fairly
    -1.09
     part
    -1.05
    
    -1.05
     very
    -1.03
     soupe
    -1.03
    UTELY
    -1.02
     quite
    -1.02
    vula
    -1.02
    Dtor
    -1.01
    POSITIVE LOGITS
     than
    2.13
     about
    1.58
     this
    1.39
     why
    1.19
     including
    1.16
     of
    1.15
     details
    1.14
     on
    1.13
     these
    1.12
    进一步
    1.08
    Activations Density 0.034%

    No Known Activations