© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113598
    Prev
    Next
    INDEX
    Explanations

    people and brands names

    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
     vuestro
    -1.72
     limpi
    -1.66
    сети
    -1.59
    。
    -1.59
     verdaderamente
    -1.51
     siquiera
    -1.49
    。(
    -1.48
    英国
    -1.48
     küm
    -1.46
    じゃなくて
    -1.46
    POSITIVE LOGITS
     to
    2.94
    お楽しみに
    1.63
     проекты
    1.59
    </strong>
    1.58
    lo
    1.55
    心中的
    1.53
    很快就
    1.52
     names
    1.51
    Nombres
    1.48
    但她
    1.48
    Activations Density 0.016%

    No Known Activations