© 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. 70710
    Prev
    Next
    INDEX
    Explanations

    sampling methods and contexts

    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
     ‘
    -3.22
    '
    -2.83
    一旁
    -2.41
    !”
    -2.39
    );
    -2.34
    )」
    -2.27
     (‘
    -2.25
    ’
    -2.25
    后
    -2.23
     {
    -2.14
    POSITIVE LOGITS
    沨
    3.06
    艄
    2.80
    鶿
    2.63
    𞤢
    2.58
    臯
    2.53
    鸶
    2.52
    ၞ
    2.50
    磲
    2.42
    要不是
    2.41
    賔
    2.38
    Activations Density 0.004%

    No Known Activations