© 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. 14476
    Prev
    Next
    INDEX
    Explanations

    Zombie, outlandish names, specific professions, and topics

    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
    }(
    -1.90
     in
    -1.87
    ྜ
    -1.83
    了啊
    -1.82
    i
    -1.81
    我这
    -1.70
    我没
    -1.63
     conflicts
    -1.58
    ではまた
    -1.58
    俢
    -1.57
    POSITIVE LOGITS
    '
    2.56
    vantaged
    2.09
     ก็
    2.03
     mostrarán
    1.92
    IBILITIES
    1.90
    薷
    1.88
     proposent
    1.88
     Ensuring
    1.87
    䊉
    1.83
     auront
    1.81
    Activations Density 0.034%

    No Known Activations