© 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. 34732
    Prev
    Next
    INDEX
    Explanations

    Monte Carlo, parameter, distribution, encoder, negativity

    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
    ęcie
    -1.13
    continued
    -1.10
     it
    -1.09
     deleteUser
    -1.08
    ὖ
    -1.06
     lecker
    -1.05
    此事
    -1.04
    ₱
    -1.04
    rami
    -1.04
     oil
    -1.04
    POSITIVE LOGITS
    我们
    1.30
    زندگی
    1.27
    我們
    1.20
    ִים
    1.13
    Mereka
    1.12
    𓂂
    1.10
    Tapi
    1.08
     çünkü
    1.08
    ıyoruz
    1.06
     variaciones
    1.06
    Activations Density 0.002%

    No Known Activations