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. 47508
    Prev
    Next
    INDEX
    Explanations

    Ryzen, Core, Slice, bands

    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
     возника
    1.45
    昃
    1.12
    evolving
    1.10
     существуют
    1.07
    tic
    1.04
     распростран
    1.00
    existent
    1.00
    飧
    0.99
    developing
    0.99
     respectful
    0.98
    POSITIVE LOGITS
    ার
    1.27
    𝒐
    1.18
    atorio
    1.16
    ार
    1.16
     lít
    1.13
    er
    1.12
     Bxg
    1.11
    âce
    1.10
    hibition
    1.09
    𝒔
    1.09
    Activations Density 0.004%

    No Known Activations