© 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. 146858
    Prev
    Next
    INDEX
    Explanations

    TV SHOW, struggle, pet, Santa

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

    Portuguese flair and pirate style

    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
     assessing
    0.51
     absence
    0.49
     unplanned
    0.48
     untimely
    0.47
    က
    0.47
     escena
    0.45
     totaled
    0.43
    ofen
    0.43
     Chancen
    0.43
     emblematic
    0.43
    POSITIVE LOGITS
    am
    0.57
    é
    0.57
    et
    0.52
    epsilon
    0.51
    ag
    0.48
    or
    0.47
     Xe
    0.46
    e
    0.46
    AB
    0.46
    an
    0.45
    Activations Density 0.000%

    No Known Activations