© 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. 128897
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words

    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
    ();
    -1.24
     will
    -1.20
    ׇ
    -1.16
     понрави
    -1.16
    ⡿
    -1.15
    ₅
    -1.13
    dientes
    -1.09
     будет
    -1.08
     ở
    -1.07
    εις
    -1.07
    POSITIVE LOGITS
    recently
    1.45
    噜
    1.38
    significantly
    1.31
     السياس
    1.27
    HasColumn
    1.26
    Égypte
    1.26
     strøm
    1.23
    ּוֹ
    1.23
     SHOWING
    1.23
     detalj
    1.19
    Activations Density 0.012%

    No Known Activations