© 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. 35285
    Prev
    Next
    INDEX
    Explanations

    Q: or A:

    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
    saucony
    -1.26
     aşk
    -1.19
     deň
    -1.11
    ==(
    -1.11
    还是要
    -1.09
    decken
    -1.09
     :{
    -1.08
    :[{
    -1.06
     péro
    -1.05
    гряз
    -1.05
    POSITIVE LOGITS
     H
    1.15
     N
    1.12
     دیگر
    0.97
     C
    0.97
    :
    0.96
     M
    0.95
     B
    0.94
     L
    0.94
     G
    0.93
     E
    0.93
    Activations Density 0.000%

    No Known Activations