© 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. 180124
    Prev
    Next
    INDEX
    Explanations

    Clinics and North America publications

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

    notes, scents, and timelines

    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
    Chicken
    0.48
    Levels
    0.48
    With
    0.47
     HAVING
    0.47
    ᱘
    0.47
    полу
    0.46
    Identifying
    0.46
    Using
    0.45
    ással
    0.44
    𝓇
    0.44
    POSITIVE LOGITS
     informe
    0.46
    แจ้ง
    0.46
     incite
    0.44
     అలాంటి
    0.44
     affront
    0.43
     ज्ञ
    0.43
     cha
    0.43
     conto
    0.43
    CuO
    0.43
     sneak
    0.42
    Activations Density 0.001%

    No Known Activations