© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73774
    Prev
    Next
    INDEX
    Explanations

    field associations and leagues

    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
     your
    -1.63
     or
    -1.54
     utara
    -1.44
    にします
    -1.37
     our
    -1.35
     یکی
    -1.34
     faldas
    -1.32
     січня
    -1.30
    Après
    -1.28
     malheure
    -1.28
    POSITIVE LOGITS
    <bos>
    2.06
    ebly
    1.67
     facultad
    1.37
    がありますが
    1.37
    但是在
    1.34
    在这种
    1.33
    所以在
    1.30
    anyahu
    1.30
     сумму
    1.25
     delegación
    1.24
    Activations Density 0.105%

    No Known Activations