© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12798
    Prev
    Next
    INDEX
    Explanations

    explaining what is meant

    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
    鋱
    -1.76
    atru
    -1.72
     cercana
    -1.72
     hvis
    -1.68
     protectora
    -1.63
     isolada
    -1.63
    klas
    -1.60
     abiertos
    -1.57
     решений
    -1.55
    apellido
    -1.55
    POSITIVE LOGITS
     of
    1.98
     \
    1.70
     \\
    1.68
    er
    1.67
    s
    1.66
    ans
    1.63
    ),
    1.59
    ate
    1.59
    lia
    1.58
     \&
    1.57
    Activations Density 0.008%

    No Known Activations