© 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. 76633
    Prev
    Next
    INDEX
    Explanations

    invention level

    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
    '
    0.54
     japonais
    0.48
     hammer
    0.45
     ton
    0.43
    ong
    0.43
     charge
    0.42
     warrant
    0.42
     charger
    0.42
    ım
    0.42
     transporter
    0.42
    POSITIVE LOGITS
     रहती
    0.59
     رہتا
    0.54
     रहता
    0.52
     ആവശ്യ
    0.50
    Situ
    0.48
    𝐤
    0.48
     감사합니다
    0.48
     நூ
    0.46
    ]._
    0.45
    Pun
    0.44
    Activations Density 0.002%

    No Known Activations