© 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. 11255
    Prev
    Next
    INDEX
    Explanations

    give an estimate

    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
     satria
    -1.44
     haup
    -1.25
     увлаж
    -1.23
     kotak
    -1.15
     در
    -1.15
     cincin
    -1.14
    ztés
    -1.13
    -1.13
     bukit
    -1.12
    恚
    -1.10
    POSITIVE LOGITS
    Vlastnosti
    1.28
     mochilas
    1.28
     artikkeli
    1.27
     protocolos
    1.23
     cucharadas
    1.18
    jesus
    1.13
    ená
    1.11
     turistas
    1.11
     údaj
    1.11
     arrangements
    1.10
    Activations Density 0.014%
    No Known Activations