© 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. 98651
    Prev
    Next
    INDEX
    Explanations

    spine and title

    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
    Insn
    -0.94
    windig
    -0.84
     ejecuta
    -0.82
    ății
    -0.79
    oopy
    -0.78
    ających
    -0.77
    ofos
    -0.75
    laar
    -0.74
    ceau
    -0.73
    thaus
    -0.73
    POSITIVE LOGITS
     spine
    1.35
    spine
    1.09
    TITLE
    1.08
     title
    1.08
     titles
    0.98
    Spine
    0.94
     títulos
    0.92
     leather
    0.90
    title
    0.90
    Title
    0.90
    Activations Density 0.009%

    No Known Activations