© 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. 70793
    Prev
    Next
    INDEX
    Explanations

    mathematical and code expressions

    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
     from
    -1.41
     that
    -1.34
    إنه
    -1.12
    служба
    -1.09
    殭
    -1.06
    hidup
    -1.05
     Temperaturen
    -1.05
    ಒ
    -1.04
     コス
    -1.02
    してみてください
    -1.02
    POSITIVE LOGITS
    そして
    1.38
    」
    1.13
    "
    1.07
    ">
    1.06
    特别是
    1.05
    J
    1.01
    tać
    0.96
    还要
    0.96
     uniquement
    0.95
    akterysty
    0.94
    Activations Density 0.020%

    No Known Activations