© 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. 166696
    Prev
    Next
    INDEX
    Explanations

    lengths of

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

    domain names

    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
    á
    0.54
    abbr
    0.52
    n
    0.50
    ás
    0.49
    dq
    0.46
    nél
    0.46
    nání
    0.45
    où
    0.45
    nements
    0.45
    art
    0.44
    POSITIVE LOGITS
     [])
    0.52
     फरवरी
    0.49
     ())
    0.48
     mullet
    0.48
     “”
    0.47
     rolle
    0.46
     Federalist
    0.46
     polypropylene
    0.45
     "")
    0.45
     )),
    0.45
    Activations Density 0.001%

    No Known Activations