© 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. 36144
    Prev
    Next
    INDEX
    Explanations

    navigation system elements

    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
    2
    -2.53
    </strong>
    -2.45
    鹮
    -2.33
    0
    -2.22
     Of
    -2.20
     намного
    -2.09
    軚
    -2.08
    纡
    -2.02
    en
    -1.84
    Of
    -1.80
    POSITIVE LOGITS
    ଃ
    2.86
    狆
    2.72
    ᯾
    2.64
    釔
    2.56
    ㉕
    2.44
    聍
    2.38
     hermos
    2.20
    🛇
    2.11
    婠
    2.09
    咂
    2.08
    Activations Density 0.008%

    No Known Activations