© 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. 199184
    Prev
    Next
    INDEX
    Explanations

    survive

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

    longer periods

    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
    وج
    0.46
    François
    0.43
    oges
    0.42
    籙
    0.42
    édia
    0.41
     लिखने
    0.41
     Jérôme
    0.40
     surged
    0.38
     Alexandre
    0.38
    <bbox>
    0.38
    POSITIVE LOGITS
    ঞ্চ
    0.49
     adquis
    0.49
    御
    0.49
    री
    0.47
    ব
    0.47
    রির
    0.47
    랑
    0.46
    ת
    0.45
    라서
    0.44
     oryginal
    0.43
    Activations Density 0.001%

    No Known Activations