© 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. 34-GEMMASCOPE-RES-131K
    7. 60501
    Prev
    Next
    INDEX
    Explanations

    given names followed by surnames

    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_34/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
     likelihood
    -1.29
     latina
    -1.25
    ctuaries
    -1.19
    ederen
    -1.16
    刳
    -1.12
    重要な
    -1.09
    Lipid
    -1.09
     Prevents
    -1.09
     Exquisite
    -1.08
    Libro
    -1.07
    POSITIVE LOGITS
    ?"
    1.26
    ?...
    1.17
    itize
    1.14
    ؟
    1.11
    vereign
    1.09
    ALSO
    1.09
    ...»
    1.06
    ?'
    1.06
     internetu
    1.05
    
    1.05
    Activations Density 0.044%

    No Known Activations