© 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. 110594
    Prev
    Next
    INDEX
    Explanations

    finding patterns in lists

    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
    ⚉
    0.40
    THERS
    0.39
     পরিবারের
    0.39
    Historical
    0.38
     famille
    0.37
     جوړونکي
    0.37
    সিদ্ধ
    0.37
    撵
    0.37
    raded
    0.37
    Marne
    0.36
    POSITIVE LOGITS
     unconscious
    0.44
     unconsciously
    0.41
     unknowingly
    0.39
     داخل
    0.39
    繰り返
    0.38
     zanim
    0.38
    িউ
    0.38
     répét
    0.38
     frightening
    0.37
    across
    0.37
    Activations Density 0.003%

    No Known Activations