© 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. 79036
    Prev
    Next
    INDEX
    Explanations

    transitioning to new roles

    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
    これから
    -1.13
    ಇ
    -0.98
    今まで
    -0.94
    ALTH
    -0.94
    ⽼
    -0.88
    年生
    -0.87
    торт
    -0.86
    ıza
    -0.86
    Nhap
    -0.85
    Мо
    -0.84
    POSITIVE LOGITS
     move
    1.19
    に移
    1.16
     then
    1.15
     moved
    1.04
     went
    1.04
     accepted
    1.02
     wechsel
    1.02
     took
    0.98
     became
    0.98
     accept
    0.97
    Activations Density 0.059%

    No Known Activations