© 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. 12554
    Prev
    Next
    INDEX
    Explanations

    hence why

    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
    甞
    -2.70
    </th>
    -2.59
    闿
    -2.55
    栳
    -2.55
     которы
    -2.47
    </u>
    -2.33
     pero
    -2.30
    缡
    -2.27
     однако
    -2.25
    蜴
    -2.25
    POSITIVE LOGITS
    ,
    3.14
    "
    2.61
    是
    2.34
    一直
    2.28
    Around
    2.25
     gewor
    2.11
    ‪.‬‬
    2.09
    T
    2.09
    Trying
    2.06
     Logement
    2.06
    Activations Density 0.004%

    No Known Activations