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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 670
    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-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
    Not in Any Lists

    No Comments

    Negative Logits
    গুলোর
    0.40
    গুলো
    0.38
    )").
    0.38
    쾺
    0.37
    alada
    0.36
    olute
    0.36
    ⑰
    0.36
    燾
    0.35
    }).
    0.35
     уто
    0.35
    POSITIVE LOGITS
     interest
    0.53
     Interest
    0.46
    Interest
    0.42
     计算
    0.42
     Calculation
    0.41
     Calculations
    0.41
     CALCUL
    0.40
     interes
    0.39
     Calculator
    0.39
     Calculates
    0.39
    Activations Density 0.000%

    No Known Activations