© 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. 77979
    Prev
    Next
    INDEX
    Explanations

    non-English text or punctuation

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

    budget, loan, cloud, holiday

    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
     आणि
    1.00
     અને
    0.96
     ਅਤੇ
    0.89
     और
    0.86
     và
    0.84
     এবং
    0.80
     и
    0.79
    ແລະ
    0.79
    และ
    0.74
     ແລະ
    0.74
    POSITIVE LOGITS
     ۔
    0.64
    ۔
    0.53
    uther
    0.45
     Même
    0.45
     bersifat
    0.45
    sin
    0.44
     ।
    0.44
    ።
    0.44
    pat
    0.43
    sa
    0.43
    Activations Density 0.069%

    No Known Activations