© 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. 103115
    Prev
    Next
    INDEX
    Explanations

    sheet music, metal, or folding

    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
    ˹
    -0.91
    GEORGE
    -0.91
     hul
    -0.90
    ills
    -0.88
    hydrogen
    -0.88
     """
    -0.86
    ütfen
    -0.82
    cista
    -0.82
    emplacement
    -0.82
     Bomber
    -0.82
    POSITIVE LOGITS
    '
    1.27
     Sheet
    1.08
     metal
    1.01
     music
    1.00
     Music
    0.91
    Sheet
    0.90
    For
    0.88
    (
    0.87
     aseg
    0.87
     металла
    0.86
    Activations Density 0.014%

    No Known Activations