© 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. 11163
    Prev
    Next
    INDEX
    Explanations

    US v. name, date

    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
     to
    -1.45
     as
    -1.34
     and
    -1.33
     until
    -1.17
     with
    -1.13
     because
    -1.11
     on
    -1.06
     by
    -1.00
     when
    -0.99
     instead
    -0.99
    POSITIVE LOGITS
     necesarios
    1.15
    
    1.13
     construite
    1.00
     heral
    0.99
     maniere
    0.97
    "../
    0.97
     investimentos
    0.96
    imensional
    0.95
    靦
    0.94
    <0xF4>
    0.93
    Activations Density 0.040%

    No Known Activations