© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99156
    Prev
    Next
    INDEX
    Explanations

    A: followed by colon or Gujarat

    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
     its
    -1.95
     "
    -1.77
    '
    -1.60
     was
    -1.56
    "
    -1.51
    ↵↵
    -1.48
     '
    -1.41
    ’
    -1.41
    ("
    -1.41
    o
    -1.41
    POSITIVE LOGITS
    Both
    1.45
    wnątrz
    1.44
     Scritto
    1.43
     bardak
    1.42
    givings
    1.41
    Regardless
    1.39
    Hauteur
    1.38
     emisiones
    1.35
    ducers
    1.34
    🕗
    1.31
    Activations Density 0.057%

    No Known Activations