© 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. 68830
    Prev
    Next
    INDEX
    Explanations

    Luna surname

    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
    劻
    -2.94
    on
    -2.91
    蜴
    -2.64
    at
    -2.59
    With
    -2.53
    They
    -2.42
    结语
    -2.34
    The
    -2.33
    but
    -2.22
    pregunt
    -2.20
    POSITIVE LOGITS
    StoryboardSegue
    2.58
     シルエット
    2.58
    簠
    2.55
    ſſen
    2.33
    冏
    2.31
    ޝ
    2.28
    andafter
    2.27
     正面
    2.23
    燹
    2.23
    kabau
    2.22
    Activations Density 0.007%

    No Known Activations