© 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. 70982
    Prev
    Next
    INDEX
    Explanations

    introducing a reason or context

    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
     through
    -1.84
     resolute
    -1.72
     informieren
    -1.70
    from
    -1.69
     Kühlschrank
    -1.67
    the
    -1.66
     begleiten
    -1.63
    ၜ
    -1.63
    鋮
    -1.61
     eleven
    -1.57
    POSITIVE LOGITS
    ay
    2.03
     zoude
    1.95
    蕺
    1.90
    薷
    1.87
    appointed
    1.82
    畧
    1.80
     ſou
    1.77
    ᆞ
    1.77
    蜮
    1.75
    氈
    1.74
    Activations Density 0.003%

    No Known Activations