© 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. 73839
    Prev
    Next
    INDEX
    Explanations

    works [manner 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
    翆
    -2.73
    𓐍
    -2.69
    炱
    -2.59
     norvég
    -2.53
    UTIVE
    -2.52
    ꯲
    -2.48
     декабря
    -2.42
    ⡪
    -2.39
    鹛
    -2.39
    嘬
    -2.39
    POSITIVE LOGITS
    If
    3.38
    It
    3.05
     
    2.88
    '
    2.77
    They
    2.58
    In
    2.55
    ly
    2.47
    .
    2.45
    When
    2.44
    </h3>
    2.42
    Activations Density 0.014%

    No Known Activations