© 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. 9394
    Prev
    Next
    INDEX
    Explanations

    strong 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
    </strong>
    -3.17
    ↵
    -2.86
     spearheaded
    -2.63
    떳
    -2.59
     ´
    -2.53
     _______
    -2.47
    of
    -2.45
    铙
    -2.39
          
    -2.31
    ’
    -2.30
    POSITIVE LOGITS
    ）：
    2.61
     또는
    2.55
    стреча
    2.50
    禇
    2.48
    ～。
    2.45
     Saltar
    2.44
    蒹
    2.41
     reviewing
    2.39
    。《
    2.39
    玏
    2.38
    Activations Density 0.023%

    No Known Activations