© 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. 118527
    Prev
    Next
    INDEX
    Explanations

    simple nouns following determiners

    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
    ylo
    -0.85
     OGSÅ
    -0.84
     deberá
    -0.82
     なっ
    -0.81
    DockStyle
    -0.79
     tendrá
    -0.79
     assemble
    -0.79
    rira
    -0.76
     artísticas
    -0.75
     problém
    -0.74
    POSITIVE LOGITS
     strife
    1.30
     plight
    1.08
     peers
    0.98
     
    0.94
    😪
    0.92
    😫
    0.91
     fuss
    0.91
     fui
    0.88
    ི
    0.88
    lore
    0.88
    Activations Density 0.101%

    No Known Activations