© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1019
    Prev
    Next
    INDEX
    Explanations

    hyphens and dashes

    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
    </sub>
    -1.73
    альных
    -1.68
    </h3>
    -1.55
    )=
    -1.49
    >().
    -1.46
     بعض
    -1.46
    )’
    -1.41
    czyny
    -1.40
     +=
    -1.38
    .}\
    -1.37
    POSITIVE LOGITS
    3
    1.60
     الثانية
    1.44
    えたら
    1.36
     is
    1.31
    待って
    1.31
    iapkan
    1.25
    1
    1.21
     następ
    1.19
    2
    1.18
    5
    1.17
    Activations Density 0.017%

    No Known Activations