Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 41059
    Prev
    Next
    INDEX
    Explanations

    compound interest formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
     subscript
    0.89
     equality
    0.84
     தச
    0.81
    髯
    0.80
     দয়া
    0.80
    耻
    0.78
     rectal
    0.78
     whitespace
    0.78
     malla
    0.77
     length
    0.77
    POSITIVE LOGITS
    EIN
    0.73
     взаимо
    0.71
    ين
    0.64
    rane
    0.64
    ts
    0.63
    ډ
    0.63
    нос
    0.61
    गाई
    0.61
    טי
    0.60
     транспорти
    0.60
    Activations Density 0.001%

    No Known Activations