© 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. 43994
    Prev
    Next
    INDEX
    Explanations

    Brookings Institute realm contract

    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
     业
    -2.08
     strenuous
    -2.05
     脸
    -1.77
    想い
    -1.74
     eût
    -1.73
    ꦩ
    -1.73
     schöne
    -1.73
     starke
    -1.70
    气息
    -1.69
     empê
    -1.68
    POSITIVE LOGITS
    ные
    1.89
    の新
    1.88
    They
    1.80
    鬟
    1.67
    去
    1.66
    ]
    1.65
    ์
    1.65
     nuove
    1.65
     leur
    1.59
    It
    1.57
    Activations Density 0.002%

    No Known Activations