© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38351
    Prev
    Next
    INDEX
    Explanations

    materials, compounds, and structures

    np_acts-logits-general · gemini-2.5-flash-lite

    chemical compounds and materials in scientific/technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     segnal
    -1.28
     beoor
    -1.23
     fühlte
    -1.21
     hörte
    -1.20
    problemas
    -1.16
     męski
    -1.13
    stupid
    -1.11
     手機
    -1.11
    тельству
    -1.09
     construite
    -1.05
    POSITIVE LOGITS
    สามารถ
    1.41
    TResult
    1.10
    亮相
    1.08
     pulgadas
    1.04
     можете
    1.03
    Vaata
    1.00
    like
    1.00
     MotionEvent
    0.98
    leyebilirsiniz
    0.98
     ratón
    0.98
    Activations Density 0.310%

    No Known Activations