© 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. 34-GEMMASCOPE-RES-131K
    7. 58483
    Prev
    Next
    INDEX
    Explanations

    language and associated roles/concepts

    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_34/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
     czerw
    -0.98
    赚钱
    -0.96
     scén
    -0.95
    ︓
    -0.95
    bruce
    -0.95
    のようです
    -0.95
     město
    -0.95
    Migrate
    -0.94
    鼉
    -0.94
    问道
    -0.93
    POSITIVE LOGITS
     spoken
    1.65
     barrier
    1.57
     skills
    1.51
    speaking
    1.36
     proficiency
    1.32
     speaking
    1.25
     translation
    1.20
    spoken
    1.19
     language
    1.15
    language
    1.13
    Activations Density 0.025%

    No Known Activations