© 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. 176763
    Prev
    Next
    INDEX
    Explanations

    disappeared,指摘, disappearance

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

    flatter or whispers

    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
     scaling
    0.50
     macer
    0.50
     gourmet
    0.46
     dienst
    0.45
     fractions
    0.44
     Fractions
    0.43
     Scaling
    0.43
    㳻
    0.42
     평
    0.42
     units
    0.41
    POSITIVE LOGITS
    指摘
    0.46
     Америки
    0.45
    消失
    0.45
    alleg
    0.45
     ఎమ్మెల్యే
    0.44
     উপকৃত
    0.44
     demuestra
    0.43
    wakeup
    0.41
    prism
    0.41
     disappeared
    0.40
    Activations Density 0.001%

    No Known Activations