© 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. 31-GEMMASCOPE-2-RES-262K
    7. 129613
    Prev
    Next
    INDEX
    Explanations

    punctuation and foreign words

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

    or words with abbreviations

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     erzählen
    0.50
     Vando
    0.49
     commemorated
    0.48
     Huy
    0.46
     Siegfried
    0.46
     EXISTS
    0.45
     Zentrum
    0.44
     Schönheit
    0.44
     -=
    0.44
     Zuge
    0.44
    POSITIVE LOGITS
    etro
    0.46
    ऑफ
    0.46
    एस
    0.44
    ain
    0.44
    screw
    0.43
    மின்றி
    0.42
     концу
    0.42
    ವಾಡ
    0.42
    ईद
    0.42
    менить
    0.41
    Activations Density 0.002%

    No Known Activations