© 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. 10-GEMMASCOPE-RES-131K
    7. 73056
    Prev
    Next
    INDEX
    Explanations

    far followed by direction

    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
    剮
    -3.23
    䊐
    -2.94
     elef
    -2.83
     proteine
    -2.81
     ſtate
    -2.77
     escondido
    -2.73
     bocas
    -2.70
     ͡°
    -2.69
     balas
    -2.63
    Amical
    -2.59
    POSITIVE LOGITS
    er
    3.88
    2
    3.41
    3
    3.23
    u
    2.91
    f
    2.89
     When
    2.86
    e
    2.86
     That
    2.86
    b
    2.84
     After
    2.83
    Activations Density 0.017%

    No Known Activations