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. 17-GEMMASCOPE-2-RES-65K
    4. 47514
    Prev
    Next
    INDEX
    Explanations

    fake, real, and money

    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_17_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
     ascertained
    1.14
    g
    1.06
    gu
    1.04
    ɢ
    1.03
    calcular
    1.03
    বঙ্গ
    1.02
    gado
    0.98
    ालय
    0.98
     inflicting
    0.98
    ্বর
    0.97
    POSITIVE LOGITS
    Vanilla
    0.85
    ^{
    0.84
    ος
    0.84
    Provenance
    0.84
    tidyverse
    0.84
     Iterator
    0.83
     auctioned
    0.83
     содержимое
    0.82
    Callbacks
    0.80
    रूप
    0.80
    Activations Density 0.011%

    No Known Activations