© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104761
    Prev
    Next
    INDEX
    Explanations

    locations and codes

    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
    fraid
    -1.20
     artesanato
    -1.20
    parently
    -1.12
    presumably
    -1.11
     CELEBR
    -1.05
    apparently
    -1.05
    fordable
    -1.03
    らく
    -1.03
    necessarily
    -1.03
     GUARANTEE
    -1.02
    POSITIVE LOGITS
     or
    1.90
     and
    1.14
     will
    1.08
     để
    1.03
     奈
    0.99
    after
    0.96
     childcare
    0.94
    떄
    0.94
    zaamheid
    0.93
     nemico
    0.93
    Activations Density 0.001%

    No Known Activations