© 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. 73113
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and solutions

    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
    २
    -1.04
    cokinetic
    -0.95
     roj
    -0.91
     so
    -0.90
    ！”
    -0.90
     and
    -0.90
    iotensin
    -0.90
    ClientRect
    -0.90
    mene
    -0.90
    }_{
    -0.87
    POSITIVE LOGITS
     diagnóstico
    1.03
    ʮ
    0.94
     dudas
    0.93
     ajustado
    0.91
    やりたい
    0.91
     desafío
    0.91
     ogól
    0.91
    いかない
    0.90
     pescoço
    0.90
    lateinit
    0.90
    Activations Density 0.083%

    No Known Activations