© 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. 14342
    Prev
    Next
    INDEX
    Explanations

    European Union institutions and policies

    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
    ści
    1.24
    as
    1.08
     kullanılan
    1.04
     waktu
    1.02
     nur
    1.02
    ycin
    0.97
    sez
    0.94
    ी
    0.94
    s
    0.93
    ت
    0.91
    POSITIVE LOGITS
    rope
    1.74
     égard
    1.58
     acabó
    1.43
    lemagne
    1.40
     parliament
    1.39
     Parliament
    1.38
    european
    1.37
     treaties
    1.36
    countries
    1.35
    Commission
    1.33
    Activations Density 0.019%

    No Known Activations