© 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. 25959
    Prev
    Next
    INDEX
    Explanations

    phrases following a specific word

    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
     塗装
    -1.23
     ridiculous
    -1.23
     ludicrous
    -1.17
     tatu
    -1.14
     incredibly
    -1.13
    CLUS
    -1.12
     ridiculously
    -1.12
    meris
    -1.10
     kiu
    -1.09
    gæ
    -1.08
    POSITIVE LOGITS
     after
    1.40
    民眾
    1.34
     their
    1.27
    ᐈ
    1.27
    faithful
    1.23
    Ḍ
    1.16
    üks
    1.13
     —
    1.13
     at
    1.12
    After
    1.11
    Activations Density 0.090%

    No Known Activations