© 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. 79921
    Prev
    Next
    INDEX
    Explanations

    this

    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
     Versuche
    -0.95
    araoh
    -0.92
    цыі
    -0.90
    océan
    -0.87
    ourcen
    -0.87
     nevoie
    -0.87
    Anime
    -0.87
    PAIGN
    -0.85
     traducir
    -0.85
    ומית
    -0.85
    POSITIVE LOGITS
     phenomena
    1.13
    現象
    1.01
     phenomenon
    0.98
     oppure
    0.91
     bertanya
    0.91
     informations
    0.89
    }>
    0.88
    上記の
    0.87
    __;
    0.85
     Frankrijk
    0.84
    Activations Density 0.054%

    No Known Activations