© 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. 10-GEMMASCOPE-RES-131K
    7. 7771
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessives

    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_10/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
    𝙜
    -1.27
     några
    -1.26
    SOME
    -1.25
     taką
    -1.24
    Ԁ
    -1.23
     you
    -1.21
    inghouse
    -1.20
    ဴ
    -1.20
     nogle
    -1.18
     ponieważ
    -1.18
    POSITIVE LOGITS
    桡
    1.44
     the
    1.29
    1.26
     but
    1.25
     toreb
    1.23
     cocción
    1.23
    urns
    1.22
     communs
    1.20
     schien
    1.20
    背后的
    1.16
    Activations Density 0.086%

    No Known Activations