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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 257
    Prev
    Next
    INDEX
    Explanations

    system directory paths

    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
     ./
    0.56
     './
    0.55
    ./
    0.52
     ../
    0.52
     '../../
    0.51
    none
    0.49
     ligados
    0.48
    "./
    0.48
     "./
    0.48
    ../../
    0.48
    POSITIVE LOGITS
     Hibernate
    0.67
     Hyun
    0.65
    竰
    0.64
    ουλ
    0.63
     mPreview
    0.63
     Gerr
    0.62
    โยชน์
    0.62
     Vivek
    0.62
    ymce
    0.62
     Uw
    0.61
    Activations Density 0.033%

    No Known Activations