© 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. 67995
    Prev
    Next
    INDEX
    Explanations

    navigation

    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
    </strong>
    -2.77
    鹮
    -2.75
    </h3>
    -2.75
    0
    -2.56
    which
    -2.52
    </em>
    -2.44
     οποίο
    -2.39
    乆
    -2.39
     Which
    -2.20
     ซึ่ง
    -2.16
    POSITIVE LOGITS
    }$
    2.78
    螅
    2.64
    蕷
    2.53
    ଃ
    2.52
     he
    2.52
    翃
    2.50
    薷
    2.48
    ﹣
    2.36
     defies
    2.33
     "'
    2.31
    Activations Density 0.003%

    No Known Activations