© 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-65K
    7. 14024
    Prev
    Next
    INDEX
    Explanations

    prevent errors or word splitting

    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
     входя
    0.46
     बत्रा
    0.45
     compens
    0.45
     конвер
    0.43
     Ρ
    0.42
    bibinfo
    0.42
     متعدد
    0.42
    ścić
    0.42
     ინ
    0.41
     रफी
    0.41
    POSITIVE LOGITS
    時間
    0.47
    海の
    0.45
    вла
    0.44
    з
    0.44
     evaluation
    0.43
     Unavailable
    0.43
    availability
    0.42
    ва
    0.42
    muy
    0.41
     Box
    0.41
    Activations Density 0.012%

    No Known Activations