© 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. 105
    Prev
    Next
    INDEX
    Explanations

    LaTeX mathematical expressions

    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
    6
    -3.11
    1
    -3.03
    4
    -2.86
    ８
    -2.72
    Tempat
    -2.72
    Two
    -2.64
    辚
    -2.63
    7
    -2.55
    ５
    -2.55
    Pendidikan
    -2.47
    POSITIVE LOGITS
    y
    3.19
    </h3>
    3.13
    re
    3.08
    e
    3.05
    in
    3.03
    </strong>
    3.03
    al
    2.98
    te
    2.88
    h
    2.86
    ra
    2.80
    Activations Density 0.004%

    No Known Activations