© 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. 73836
    Prev
    Next
    INDEX
    Explanations

    achieve this

    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
    縢
    -2.44
    俛
    -2.27
    鲀
    -2.23
    蠖
    -2.03
     unhappy
    -2.02
     उसकी
    -2.00
    ᄍ
    -1.99
     archaic
    -1.98
    鸝
    -1.98
    脔
    -1.98
    POSITIVE LOGITS
    s
    3.28
    g
    2.42
    [
    2.34
    {
    2.22
    (
    2.16
     людей
    2.11
    up
    2.11
     
    2.03
    "
    2.02
     There
    1.94
    Activations Density 0.015%

    No Known Activations