© 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. 12966
    Prev
    Next
    INDEX
    Explanations

    present value and price calculations

    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
     fillings
    0.39
    निवेश
    0.37
     snapped
    0.37
     جذب
    0.37
     upgraded
    0.35
    想
    0.35
     unfilled
    0.35
    ("_
    0.35
    つまり
    0.34
     sown
    0.34
    POSITIVE LOGITS
    anan
    0.42
    inde
    0.38
    uman
    0.36
    amai
    0.35
     پانچ
    0.35
    oban
    0.35
    leza
    0.34
    fact
    0.34
    ats
    0.33
    spacer
    0.33
    Activations Density 0.000%

    No Known Activations