© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27746
    Prev
    Next
    INDEX
    Explanations

    counts or reasons

    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
     gemeenten
    -1.39
     zaterdag
    -1.30
    ₱
    -1.27
     belangrij
    -1.24
     tegens
    -1.21
     septiembre
    -1.20
     settembre
    -1.16
    ⌗
    -1.16
     luglio
    -1.12
    .‏
    -1.12
    POSITIVE LOGITS
     mostra
    1.36
     a
    1.34
     this
    1.32
     TAMBÉM
    1.25
    があり
    1.17
     comanda
    1.17
    盉
    1.15
     joão
    1.13
     imobili
    1.13
    Ceci
    1.10
    Activations Density 0.021%

    No Known Activations