© 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. 70690
    Prev
    Next
    INDEX
    Explanations

    whether you or your

    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
     dovr
    -1.24
     orice
    -1.19
    糅
    -1.18
     berbagai
    -1.17
     всички
    -1.16
     всіх
    -1.16
     також
    -1.14
    Кроме
    -1.14
    tembro
    -1.13
    atization
    -1.13
    POSITIVE LOGITS
     your
    1.83
     you
    1.52
    //!
    1.22
    у
    1.05
    ях
    1.05
    想要
    1.00
    lesias
    1.00
    度の
    0.99
    жений
    0.98
     Whether
    0.98
    Activations Density 0.025%

    No Known Activations