Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3718
    Prev
    Next
    INDEX
    Explanations

    viewpoint or view layer

    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_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
    ت
    1.39
     ISR
    1.04
    ма
    1.04
     λ
    1.03
    ב
    1.01
    ৯৫
    1.00
    nel
    1.00
    ك
    1.00
    magnet
    1.00
    में
    0.99
    POSITIVE LOGITS
    point
    1.51
    ers
    1.48
    erView
    1.46
    ports
    1.46
    points
    1.45
    Sonic
    1.42
    PORT
    1.38
     beschäftigt
    1.31
    POINT
    1.30
    රු
    1.29
    Activations Density 0.029%

    No Known Activations