© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 20913
    Prev
    Next
    INDEX
    Explanations

    python library paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     シェ
    0.40
    洍
    0.40
    팅
    0.38
     보이는
    0.38
     Sheehan
    0.38
    焘
    0.38
    itiba
    0.37
    INTRO
    0.37
    NING
    0.37
    শীর
    0.36
    POSITIVE LOGITS
    jvm
    0.49
     profound
    0.42
     python
    0.41
    python
    0.41
     Python
    0.40
     copos
    0.38
     pygame
    0.38
    ͎
    0.38
     plotly
    0.37
    dim
    0.36
    Activations Density 0.002%

    No Known Activations