© 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. 84199
    Prev
    Next
    INDEX
    Explanations

    changes were, surprisingly fast, last layer

    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
    ន្ទ
    0.38
     sahabat
    0.37
     próp
    0.36
     divisi
    0.35
     exempt
    0.35
     propi
    0.35
     आशा
    0.35
     prijatel
    0.35
    icyclo
    0.34
    POSITIVE LOGITS
     ಮಟ್ಟ
    0.43
    Pretty
    0.41
     characterizing
    0.41
     오
    0.40
    introduced
    0.38
    വണ
    0.38
     Tabs
    0.38
    人心
    0.38
    樊
    0.36
    δώ
    0.35
    Activations Density 0.000%

    No Known Activations