© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 36950
    Prev
    Next
    INDEX
    Explanations

    microfinance and loans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    チェーン
    0.49
     chain
    0.48
     Chain
    0.45
    नस
    0.44
    chain
    0.44
     チェーン
    0.43
    链
    0.41
    Chain
    0.41
     chaîne
    0.40
    agnet
    0.39
    POSITIVE LOGITS
     kleiner
    0.42
     Kakkar
    0.41
    Dire
    0.41
    밥
    0.41
    Ce
    0.40
     hunger
    0.40
    vere
    0.39
    izam
    0.39
     alleviated
    0.39
    rahman
    0.39
    Activations Density 0.001%

    No Known Activations