© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5969
    Prev
    Next
    INDEX
    Explanations

    German numbers, suffixes, endings

    np_acts-logits-general · gemini-2.5-flash-lite

    LMSYS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    heni
    0.42
    >&
    0.40
     yr
    0.40
    ూర్
    0.39
    oun
    0.38
     usk
    0.38
    aurant
    0.38
    hen
    0.37
    }-
    0.36
     Sunt
    0.36
    POSITIVE LOGITS
    ierend
    0.52
     entsprechend
    0.48
     vielleicht
    0.47
    izieren
    0.46
     sicher
    0.46
    ifizierung
    0.46
    istisch
    0.45
    CHREIBUNG
    0.45
     jahr
    0.45
    isiert
    0.45
    Activations Density 0.007%

    No Known Activations