© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3809
    Prev
    Next
    INDEX
    Explanations

    setting up

    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
     desenhos
    0.84
    groupby
    0.81
    災
    0.79
    Til
    0.78
     चाहि
    0.76
    toggle
    0.75
    表記
    0.75
    𝕂
    0.75
    ગવાન
    0.74
    startsWith
    0.74
    POSITIVE LOGITS
     aside
    1.66
     up
    1.45
     expectations
    1.41
     alight
    1.40
     forth
    1.36
     priorities
    1.34
     sail
    1.30
     apart
    1.25
    tting
    1.22
    aside
    1.16
    Activations Density 0.107%

    No Known Activations