© 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. 11276
    Prev
    Next
    INDEX
    Explanations

    getting used to new situations

    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
     meaningful
    -1.16
    _
    -1.08
     чаще
    -1.06
     utaf
    -1.03
    ↵↵
    -1.01
     hivyo
    -1.01
     contained
    -1.00
     every
    -1.00
     preserving
    -1.00
     therefore
    -0.96
    POSITIVE LOGITS
     yeni
    1.30
     habitu
    1.25
    🤯
    1.22
    鳊
    1.22
     new
    1.20
    ufnahme
    1.20
    椋
    1.20
    😵
    1.19
    ใหม่
    1.18
     nových
    1.16
    Activations Density 0.022%

    No Known Activations