© 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. 120311
    Prev
    Next
    INDEX
    Explanations

    location on surface

    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
    detectChanges
    0.38
     Fifty
    0.37
    ColumnCount
    0.37
     desayuno
    0.37
    Види
    0.36
    鹘
    0.36
     कराए
    0.36
    Foo
    0.36
    蝓
    0.35
     Housewives
    0.35
    POSITIVE LOGITS
    上の
    0.60
    身上
    0.58
     trên
    0.57
    บน
    0.55
    上で
    0.55
     عليها
    0.54
     üzerinde
    0.53
     عليهم
    0.49
    上的
    0.49
     sulla
    0.48
    Activations Density 0.007%

    No Known Activations