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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11205
    Prev
    Next
    INDEX
    Explanations

    conditions, criteria, and equivalences

    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_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
    まっている
    -0.94
    श्ले
    -0.94
    mauer
    -0.93
    MANAGEMENT
    -0.90
    ⬎
    -0.88
     VIDEOT
    -0.88
     OFFICIAL
    -0.86
     alcuni
    -0.85
     générer
    -0.85
     тема
    -0.84
    POSITIVE LOGITS
     something
    1.18
     conditions
    1.14
     beautiful
    1.10
     requirements
    1.06
    حدى
    1.04
     strengthen
    1.02
     хорошее
    1.02
     holds
    1.01
     helps
    1.00
     someone
    0.98
    Activations Density 0.044%

    No Known Activations