© 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. 249835
    Prev
    Next
    INDEX
    Explanations

    smaller words

    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
     beiden
    0.56
    vient
    0.56
     تقویت
    0.53
    乨
    0.53
    ('./
    0.50
    ("./
    0.49
    Noeud
    0.49
     epidermal
    0.48
     ዘዴ
    0.48
    _',
    0.48
    POSITIVE LOGITS
    。
    0.46
    sold
    0.46
    on
    0.42
    smaller
    0.42
    told
    0.42
    tell
    0.40
     I
    0.40
    c
    0.40
    terra
    0.39
     Smaller
    0.39
    Activations Density 0.000%

    No Known Activations