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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 19918
    Prev
    Next
    INDEX
    Explanations

    numbers and comparisons

    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
     jūs
    0.97
    ές
    0.94
     Erst
    0.93
    िलास
    0.93
    밭
    0.93
    ন্ধে
    0.92
     Bahkan
    0.91
    nä
    0.91
    ὶ
    0.90
    onglet
    0.90
    POSITIVE LOGITS
     exclusivity
    1.14
     magic
    1.14
     scars
    1.12
     capricious
    1.10
     demarcation
    1.10
     exuber
    1.06
     dismantled
    1.04
     goodwill
    1.02
     dismantling
    1.01
     francs
    1.01
    Activations Density 0.000%

    No Known Activations