© 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. 22-GEMMASCOPE-RES-131K
    7. 13615
    Prev
    Next
    INDEX
    Explanations

    acronyms followed by descriptions

    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_22/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
     »)
    -1.12
     ovan
    -1.09
    »:
    -1.06
    ೫
    -0.99
     their
    -0.96
    Վ
    -0.95
    (;;)
    -0.94
     talla
    -0.94
    ]');
    -0.94
     PARSER
    -0.91
    POSITIVE LOGITS
     according
    1.13
     According
    1.03
     and
    1.00
    の一つ
    0.98
     '
    0.94
     “
    0.93
     "
    0.92
    actividades
    0.92
     National
    0.91
     stifle
    0.91
    Activations Density 0.006%

    No Known Activations