© 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. 12547
    Prev
    Next
    INDEX
    Explanations

    in the traditional sense

    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
    ಥವಾ
    0.41
    ственную
    0.41
     murderous
    0.41
    ैनल
    0.40
    日光
    0.39
    ﺵ
    0.38
     ◆
    0.38
    ◆
    0.38
    クトル
    0.36
     બીજી
    0.36
    POSITIVE LOGITS
     proper
    0.57
    真正
    0.52
     egent
    0.50
     собственно
    0.48
    真正的
    0.48
     truly
    0.46
     Proper
    0.46
     proprement
    0.46
    proper
    0.45
     بمعنى
    0.43
    Activations Density 0.175%

    No Known Activations