© 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. 68036
    Prev
    Next
    INDEX
    Explanations

    by followed by a name

    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
     suggests
    -1.26
     there
    -1.26
     people
    -1.23
     these
    -1.18
     think
    -1.13
     knows
    -1.13
     loro
    -1.13
     does
    -1.12
     groups
    -1.11
     آنجا
    -1.09
    POSITIVE LOGITS
     poë
    1.39
     régiment
    1.34
     Asie
    1.34
     Italie
    1.24
    atürk
    1.23
     laurent
    1.23
     یعنی
    1.20
     vanille
    1.20
     nicolas
    1.18
    醅
    1.18
    Activations Density 0.052%

    No Known Activations