© 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. 10-GEMMASCOPE-RES-131K
    7. 1729
    Prev
    Next
    INDEX
    Explanations

    that's fine

    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_10/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
     ecosistema
    -1.51
    メリカ
    -1.22
     warme
    -1.20
    Senha
    -1.14
    tares
    -1.14
    mengg
    -1.12
    ⽼
    -1.12
     cierra
    -1.12
     afforded
    -1.12
     rapida
    -1.12
    POSITIVE LOGITS
    {
    1.55
     if
    1.55
    if
    1.36
    
    1.24
    or
    1.23
    as
    1.20
    ipolar
    1.20
     as
    1.20
    tidase
    1.20
    </h5>
    1.17
    Activations Density 0.028%

    No Known Activations