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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 350
    Prev
    Next
    INDEX
    Explanations

    regard, need, build, killed, landslide

    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_22_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
    น้อง
    1.32
    dje
    1.31
    ал
    1.29
    น
    1.29
    codes
    1.28
    க
    1.26
     следова
    1.25
    ricies
    1.25
    ы
    1.24
    hadow
    1.24
    POSITIVE LOGITS
     regard
    1.08
    ంప
    0.92
     viel
    0.84
     ving
    0.84
     romp
    0.82
    ંપ
    0.82
     decimal
    0.81
     resol
    0.81
     praising
    0.81
     kapal
    0.81
    Activations Density 0.000%

    No Known Activations