© 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. 130681
    Prev
    Next
    INDEX
    Explanations

    sender names

    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
    point
    -1.13
     deras
    -1.13
     их
    -1.08
    ഞ
    -1.05
    螓
    -1.02
    PHI
    -1.01
    اصمة
    -1.01
    man
    -1.00
    ↵
    -0.99
    黾
    -0.99
    POSITIVE LOGITS
     in
    1.21
     に関する
    1.19
     subgoal
    1.17
     infatti
    1.12
     手順
    1.10
    acamole
    1.09
     thankfully
    1.08
     impressively
    1.08
     that
    1.07
     namelijk
    1.07
    Activations Density 0.011%

    No Known Activations