© 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. 29-GEMMASCOPE-2-RES-65K
    4. 5222
    Prev
    Next
    INDEX
    Explanations

    programming practices or concepts

    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_29_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
     inputted
    0.92
     ¾
    0.81
     ‘
    0.80
    untitled
    0.80
    ⁣⁣
    0.78
     utilising
    0.78
     Utilizing
    0.77
    当下
    0.77
    🏼
    0.77
    ั้ย
    0.76
    POSITIVE LOGITS
     cryptographic
    1.18
     FreeBSD
    1.13
     Unix
    1.00
     CMake
    0.98
     filesystem
    0.97
     TypeScript
    0.95
     syntactic
    0.95
    POSIX
    0.95
     programmer
    0.94
    Linux
    0.93
    Activations Density 0.714%

    No Known Activations