© 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. 31-GEMMASCOPE-2-RES-262K
    7. 108106
    Prev
    Next
    INDEX
    Explanations

    contrast conjunctions

    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_31_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
     Chevrolet
    0.45
    柅
    0.44
     avantages
    0.44
     কামাল
    0.44
    ymptotic
    0.43
    dött
    0.43
     Tight
    0.42
     Vancouver
    0.42
    溲
    0.42
     Chevron
    0.42
    POSITIVE LOGITS
    czne
    0.51
    OGA
    0.50
    🧒
    0.48
     odnos
    0.46
    assessment
    0.46
    ಾರಿ
    0.45
     אותו
    0.45
     അവര്‍
    0.44
    operations
    0.43
    </b>
    0.42
    Activations Density 0.004%

    No Known Activations