© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7756
    Prev
    Next
    INDEX
    Explanations

    that of

    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
     experimentado
    -2.38
     but
    -2.00
     camiones
    -1.98
    Espagne
    -1.86
    Selain
    -1.84
    Berat
    -1.82
     alcanzado
    -1.78
    Tapi
    -1.73
    樯
    -1.72
     and
    -1.71
    POSITIVE LOGITS
     of
    6.09
    “
    2.11
     that
    2.05
    ]
    2.02
    n
    1.94
    of
    1.91
     to
    1.70
     “
    1.69
    S
    1.69
    for
    1.66
    Activations Density 0.039%

    No Known Activations