© 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. 34767
    Prev
    Next
    INDEX
    Explanations

    n after

    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
    ượu
    -1.16
    もとも
    -1.13
    نجليزية
    -1.05
    Чет
    -1.05
    Веду
    -1.03
     öfter
    -1.02
     أيضًا
    -1.02
    Beschrijving
    -1.01
    最近は
    -0.99
    つまり
    -0.99
    POSITIVE LOGITS
    了下去
    1.14
    {})
    1.09
    woke
    1.09
    \}}
    1.09
    llum
    1.08
     juſ
    1.07
    burner
    1.05
    }
    1.05
    ;\
    1.02
    "\
    1.00
    Activations Density 0.012%

    No Known Activations