© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 5136
    Prev
    Next
    INDEX
    Explanations

    usually often generally

    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_65k_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
     उक्त
    0.47
    padă
    0.44
    珈
    0.42
    ἂ
    0.41
     الذين
    0.40
    𝙚
    0.40
     intriguing
    0.40
    閆
    0.39
    പ്പ്
    0.39
     архів
    0.39
    POSITIVE LOGITS
     সাধারণত
    0.55
     usually
    0.55
     अक्सर
    0.53
     often
    0.50
     geralmente
    0.50
     단순히
    0.49
     meestal
    0.48
     biasanya
    0.47
     आमतौर
    0.46
     často
    0.46
    Activations Density 0.636%

    No Known Activations