© 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. 79851
    Prev
    Next
    INDEX
    Explanations

    property features or amenities

    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
     ARISING
    -1.41
     to
    -1.31
     البلد
    -1.30
    ea
    -1.26
    那就
    -1.24
    了些
    -1.23
    eng
    -1.20
     oliveira
    -1.20
    ensi
    -1.18
     disappro
    -1.17
    POSITIVE LOGITS
     and
    1.96
    dekat
    1.43
     bolsos
    1.40
     gorro
    1.27
    lepaskan
    1.21
     fasse
    1.20
    مقاله
    1.17
     around
    1.16
     szczeg
    1.13
    დი
    1.09
    Activations Density 0.009%

    No Known Activations