© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129230
    Prev
    Next
    INDEX
    Explanations

    I am asking for help

    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
    mathrm
    -1.13
     眼睛
    -1.12
    twimg
    -1.05
     mindestens
    -0.98
    merken
    -0.98
     jeden
    -0.96
     вами
    -0.90
     خودت
    -0.90
     implant
    -0.89
    ytick
    -0.89
    POSITIVE LOGITS
     my
    1.72
    Джере
    1.25
     мені
    1.19
     I
    1.19
    我这
    1.17
    りたい
    1.15
    のでしょうか
    1.12
     моих
    1.11
    开发者
    1.09
     rayures
    1.07
    Activations Density 2.384%

    No Known Activations