© 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. 99463
    Prev
    Next
    INDEX
    Explanations

    movement upwards

    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
    for
    -2.94
    0
    -2.91
    2
    -2.73
    на
    -2.63
    袮
    -2.56
     Except
    -2.48
     Including
    -2.45
     сред
    -2.42
    瑧
    -2.30
     The
    -2.23
    POSITIVE LOGITS
    ⬈
    3.16
     帅气
    3.09
    苤
    3.00
    嵛
    2.97
    滹
    2.95
    橚
    2.92
     люди
    2.91
    ࿆
    2.91
    ᯾
    2.83
    ᠁
    2.81
    Activations Density 0.003%

    No Known Activations