© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 14170
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and specific entities

    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
     o
    1.05
     contiguous
    0.97
     gegeben
    0.96
     ene
    0.95
    是有
    0.92
     исход
    0.91
     slags
    0.91
    éral
    0.91
    ृता
    0.90
    その
    0.90
    POSITIVE LOGITS
     δὲ
    1.17
    डिएटली
    1.07
    ®
    1.06
    ៣
    1.05
    manirrahim
    1.03
    acariy
    1.02
    籿
    1.01
    ®,
    1.01
    Luckily
    1.01
    Shuffle
    1.01
    Activations Density 0.296%

    No Known Activations