© 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. 84486
    Prev
    Next
    INDEX
    Explanations

    signatories

    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
    保证
    0.38
    族
    0.38
    Autowired
    0.37
    င်း
    0.36
    힝
    0.36
    isem
    0.36
    ྂ
    0.35
     asegurarse
    0.35
     authenticated
    0.34
     garantir
    0.34
    POSITIVE LOGITS
     Sign
    0.46
    Sign
    0.44
     sign
    0.43
     Yesu
    0.43
     딱
    0.42
    签字
    0.42
     signatories
    0.41
     From
    0.40
     ይመ
    0.40
     संस्कृति
    0.40
    Activations Density 0.000%

    No Known Activations