© 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. 95676
    Prev
    Next
    INDEX
    Explanations

    what is it / what about it

    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
    сяг
    -1.32
     entren
    -1.27
    Ꮉ
    -1.25
    שׂ
    -1.25
     occurs
    -1.22
     necessary
    -1.22
     hará
    -1.22
    ㍑
    -1.22
     sufficient
    -1.20
     خس
    -1.19
    POSITIVE LOGITS
     them
    1.53
     this
    1.52
     our
    1.41
     these
    1.40
     their
    1.36
     упаковка
    1.32
     it
    1.29
     your
    1.23
    return
    1.20
     /
    1.16
    Activations Density 0.035%

    No Known Activations