© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130946
    Prev
    Next
    INDEX
    Explanations

    od prefix

    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
    which
    -2.58
    derdag
    -2.52
    ],
    -2.44
     vollständ
    -2.41
    その他の
    -2.23
    ing
    -2.20
    这人
    -2.20
     "");
    -2.14
    快要
    -2.13
    または
    -2.11
    POSITIVE LOGITS
    翃
    3.11
     Then
    2.59
    는
    2.52
     allude
    2.38
    謄
    2.34
    illige
    2.31
    ﾅ
    2.31
    全世界
    2.31
    她
    2.28
    The
    2.23
    Activations Density 0.001%

    No Known Activations