© 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. 72147
    Prev
    Next
    INDEX
    Explanations

    chemical notation, addresses, and mixed languages

    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
    9
    -1.28
    〜〜
    -1.09
    〜！
    -1.07
    6
    -1.06
    It
    -1.06
    7
    -1.05
    There
    -1.05
    積極
    -1.03
     only
    -1.03
     również
    -1.02
    POSITIVE LOGITS
    wisata
    1.25
     stratégies
    1.19
     hisz
    1.16
     DIFFERENT
    1.12
    তথ্য
    1.11
     ventes
    1.11
     MÁ
    1.11
    olahan
    1.09
     rêves
    1.05
     chè
    1.05
    Activations Density 0.057%

    No Known Activations