© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3644
    Prev
    Next
    INDEX
    Explanations

    compound interest calculations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ish
    0.52
    x
    0.49
    k
    0.45
    xm
    0.40
     is
    0.39
    val
    0.38
    layout
    0.38
    c
    0.38
     {
    0.38
    phonic
    0.38
    POSITIVE LOGITS
     അതിനാ
    0.44
     scă
    0.44
     elucidation
    0.43
     ито
    0.43
     diagonalization
    0.43
     biopsies
    0.42
    驽
    0.41
    нік
    0.41
     медици
    0.41
    蒉
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.