© 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. 27303
    Prev
    Next
    INDEX
    Explanations

    dates, specific tokens, 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
     for
    -1.74
     like
    -1.42
     more
    -1.37
     should
    -1.33
     can
    -1.32
     in
    -1.31
     as
    -1.30
     not
    -1.22
     their
    -1.21
     or
    -1.20
    POSITIVE LOGITS
    푆
    1.23
    撅
    1.17
     partecipare
    1.16
    指着
    1.13
    sipasi
    1.09
     éché
    1.06
     rimanere
    1.05
    UPAC
    1.05
    ㍉
    1.03
     specif
    1.01
    Activations Density 0.000%

    No Known Activations