© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22694
    Prev
    Next
    INDEX
    Explanations

    using the word not

    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
    Negative Logits
    0
    -3.42
    1
    -3.33
    9
    -3.05
    8
    -2.92
    7
    -2.91
    6
    -2.89
    5
    -2.44
    3
    -2.41
    2
    -2.36
     Inſ
    -2.34
    POSITIVE LOGITS
     a
    2.53
     atendido
    2.23
     ALWAYS
    2.09
    </h1>
    2.06
     usadas
    2.06
    aabb
    1.98
    ']>
    1.92
    聾
    1.91
     During
    1.86
    Honors
    1.86
    Activations Density 0.059%

    No Known Activations